The W3C's accessibility guidelines encode a principle that agent builders are arriving at from the other direction: the adequacy of a description depends on what someone needs it for. A photo of a bird on a birding site needs species and plumage. The same photo on a parks page needs "bird at the lake." A printer icon used as a button should say "print," not "image of a printer."
The same logic applies to any agent-generated output. A contract summary can be thorough, well-sourced, and coherent while missing what the reader actually needed. Were they assessing risk? Checking dates? Looking for a reason to walk away? Thoroughness is not the same as adequacy, and the source material alone cannot tell you which details matter.
The W3C addressed this by requiring a human author who understands the context to decide what counts. For agents, the interesting question is what happens when that contextual judgment is precisely the thing being automated. Most agent systems today optimize for plausible completeness because completeness is measurable and purpose-fitness is not. The incentive structure rewards looking thorough over being useful.
Same image, different purpose: The W3C's alt decision tree routes authors through purpose questions before they write a word of description. What the image contains comes second.
Intent over inventory: A photo of a happy family on a company homepage? The adequate alt text is "We're a family-friendly company." You describe the message, not the pixels.
When nothing is the right answer: For purely decorative images, the W3C prescribes a null alt attribute. The adequate description is no description at all.
Compelled reliance: Researchers use this term for situations where someone depends on a description they cannot verify against the source. Detailed, confident outputs can actually discourage the further checking that would catch errors.