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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add meaningful context beyond the schema by explaining that dominant colour is 'measured from every frame of the master rather than described' — a non-obvious behavior. However, it is silent on other behavioral aspects such as read-only nature, default ordering, pagination, or rate limits. For a search tool these are less critical, but the lack of any safety/performance context keeps this at a mid score.

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 description is a single, well-organized sentence that front-loads the core action ('Search the catalogue...') and then lists the key filter dimensions. It avoids redundancy with the schema and is efficient. The only slight issue is that it does not use bullets or other structure to parse the list of filters, but given the moderate length, it remains readable and earns a 4.

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?

Given the tool's complexity (11 parameters, no output schema, no annotations), the description covers the main search and filter capabilities but omits important execution details: how results are ordered by default, how limit works, what the return payload looks like, and whether filters are combined with AND or OR. It is adequate for guiding an agent to the right tool, but not complete enough for a complex search endpoint.

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 45%, so the description must compensate for the many undocumented parameters (limit, order, sort_by, min_price, max_price). It does add some meaning by grouping filters ('price' covers the min/max range) and clarifying the colour parameter's measurement method. But it does not explain sorting options, limits, or the semantics of order asc/desc. It partially bridges the gap, but not enough to earn a 4.

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 opens with a specific verb and resource: 'Search the catalogue of 296 moving-image works by César Yagüe.' It then enumerates the filter dimensions (collection, orientation, resolution, availability, price, free text, dominant colour), which clearly distinguishes it from sibling tools like browse_collections (browsing) or get_artwork (retrieving a single record). An agent can immediately tell this is the search/filter tool.

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?

The description clearly implies when to use this tool: when you need to find works by filtering on any of the listed attributes. It does not explicitly name alternatives or state when not to use it, but the filter-focused language makes the use case obvious. There are no exclusions or misleading cues, but the lack of explicit comparison to siblings like 'rank_artworks' or 'recommend_for_space' costs the fifth point.

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