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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds genuinely new behavioral detail: return_image makes the server fetch bytes and return a max-512px downscaled preview, with a documented fallback (URL plus reason) when the fetch fails behind a WAF. It also discloses the connector version prerequisite and explains why guessing derived filenames causes live 404s.

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?

The core purpose is front-loaded in the first sentence, and the four paragraphs map cleanly to the tool's modes. It is somewhat verbose, with persuasive asides ('you would have to GUESS the "-768x347.jpg" style filenames') that could be tightened, but the length is largely justified by the four distinct call modes.

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?

An output schema exists, so return-value documentation is rightly omitted, and the description covers modes, prerequisites, and safety-relevant constraints. The remaining gap is listing behavior — pagination via page/per_page and the mime filter are never mentioned, which an agent listing a large library would need.

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 0%, so the description carries the whole burden. It meaningfully explains four of eight parameters — search (find existing image), media_id (returns one image with all intermediate sizes and srcset), return_image (requires media_id), and check_url (site-side HEAD, same-site only). However, mime, page, per_page, and site_url are left completely undocumented, so pagination and filtering behavior must be inferred from defaults.

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?

The description states a specific verb and resource (browse the media library of a connected WordPress site) and enumerates the returned fields (id, URL, alt text, dimensions). It also disambiguates the tool's other modes (media_id detail lookup, return_image preview, check_url HEAD check), so an agent can tell it apart from wordpress_upload_media or upload_image immediately.

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?

Explicit routing is provided: search by name 'instead of uploading a duplicate,' and the returned id is 'what you pass as featured_media to wordpress_create_post / wordpress_update_post.' It also states when to use return_image (match an existing image's style, confirm a file) and when to use check_url (verify a variant exists, check a link/redirect), plus the constraint that only same-site URLs are allowed.

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