wikimedia_search_media

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

Annotations already cover the safety profile (readOnly, idempotent, open-world, non-destructive), and the description goes beyond them by disclosing that results include metadata and licenses and that pagination continues via a 'gsroffset' token. That continuation detail is the genuinely valuable part, since an agent would otherwise not know how to page through results.

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?

One short sentence plus a compact constraint clause, with the core purpose front-loaded before the parameter details. Slight waste in repeating schema-encoded ranges, but no filler or redundancy in phrasing.

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 5 params, no output schema, and zero schema description coverage, the description should do more heavy lifting. It helpfully states what is returned (metadata, licenses, continuation) but leaves the media-type selector and the meaning of width unexplained, which are gaps an agent must guess at when filtering by file type.

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 0%, so the description must carry param meaning, but the only ranges it cites (limit 1–50, offset 0–10000, width 0–4096) merely restate the schema's minimum/maximum values. It never explains the 'kind' enum (all/svg/image/audio/video/pdf), the most important semantic decision for a media search, and 'width' remains ambiguous (thumbnail render width vs. filter).

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 uses a specific verb and scope ('Search Commons files') rather than a generic 'search', which separates it from Wikimedia siblings such as wikimedia_get_file and wikimedia_list_category. It does not, however, distinguish itself from wikipedia_search or wikipedia_list_images, so an agent must infer that this one targets Commons media specifically.

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?

There is no guidance on when this tool is preferred over wikimedia_list_category (browse by category), wikimedia_get_file (fetch a known file), or wikipedia_list_images. 'Ranked by relevance' hints that it is a text-relevance search, but no alternatives or exclusions are named.

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