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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description does add value beyond them by naming the external providers and by flagging the licence/credit obligation that must be carried forward to set_slide_image. It says nothing about result-cap behaviour (limit max 30), pagination, or whether results are cached/stable, so it stays at a solid 3 rather than higher.

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?

A single compact sentence that front-loads the action and providers before listing return fields and the credit handoff. Dense but every clause carries information; the enumerated field list is slightly list-heavy but earns its place since there is no output schema. Written in French while the name/title are English, a minor consistency cost.

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 usefully enumerates the returned fields (url, thumbnail, title, author, licence, source page) and links to the follow-up tool, which is most of what an agent needs to call and use it. The remaining gaps are sibling disambiguation versus search_photos and the behaviour of the undocumented limit parameter.

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 coverage is 50%: `query` is documented in the schema with the English-keyword hint, while `limit` has no description anywhere. The description contributes no parameter meaning of its own ("photos libres" only loosely implies keyword search), so it does not compensate for the undocumented limit; baseline 3 is the fair call.

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 a specific verb and resource ("Chercher des photos libres") and names the two sources it queries (Wikimedia Commons, Openverse), plus the fields it returns, so the agent knows exactly what the call produces. It does not distinguish itself from the sibling search_photos, which looks nearly identical, so an agent cannot tell from the description which one to prefer.

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?

Usage is only implied: the parenthetical "(à passer en crédit à set_slide_image)" shows the downstream step, which hints the tool is for sourcing images for a slide. There is no explicit when-to-use/when-not guidance and no mention of when to choose this over search_photos, capture_page_images, or import_image_url.

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