Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description is free to add behavior: pagination size ('thirty photos a page') and the shape of each result (id, subject description, photographer). Since there is no output schema, this return-format disclosure is genuinely useful. It omits nothing serious, though rate limits or query-breadth behavior are unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, each doing a distinct job: source, use case, return shape, next step. The phrase 'the editor's picker as a tool' is awkward and slightly opaque, the main blemish on an otherwise dense, front-loaded description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining results and does so (30 per page, id + subject + photographer). It also covers site scoping and the intended next tool. Only the absence of guidance on search_media vs. this tool keeps it short of complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so 'site', 'query' and 'page' are already documented with examples ('heron at dawn'). The description echoes site scoping and implies page-based paging but adds no syntax or constraint beyond the schema, which is the baseline-3 case.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the specific resource — 'Free photos from Unsplash' — scoped to 'one site of the account', which is concrete enough for an agent to tell it apart from a generic media search. The verb is only implied by the tool name rather than written in the description, and the sibling search_media is never named, so differentiation is partial.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger: 'For a post that needs a picture when the person gave you none.' Also names the follow-up action ('Put one into a post with use_photo and its id'), which closes the loop. It never says when NOT to use this vs. search_media (the site's own library), leaving one likely confusion unresolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.