tes_resource_search

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, and it does substantial work: it discloses the reproduction/republication restriction and explains why only normalized facts are returned, it states that enums are closed and validated against Tes's own facet taxonomy, and it clarifies that country does not change which key_stage/subject values are valid. It does not explicitly state whether the tool is read-only or whether pagination has limits, but the read-only nature is strongly implied by 'search' and the absence of any mutation language. The behavioral context provided goes well beyond a bare 'Search Tes resources' statement.

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 dense paragraph, but every sentence earns its place: it covers the resource, the return shape, the legal/behavioral constraint, the optionality of query, the mapping of sort/key_stage/subject to the real search page, and the country semantics. It is not front-loaded in the sense of a short first sentence followed by details, but the first sentence does state the core purpose immediately. The density is high but not bloated; a slight structural improvement would be splitting into two or three sentences for readability.

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?

For a search tool with 8 optional parameters, no required parameters, no output schema, and no annotations, the description covers the essential decision space: what is returned, what is not returned, when to omit query, how filters map to the real UI, and how country behaves. The main gaps are the absence of the actual enum lists for key_stage and subject (though the description points to the endpoint markdown) and the lack of any statement about pagination defaults or page_size bounds. These are minor relative to the overall completeness.

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 the baseline is 3. The description adds meaningful semantics beyond the schema: it explains that query is optional and can be combined with filters or omitted entirely, that sort mirrors the real search page's dropdown, that key_stage and subject are closed enums from Tes's own facet taxonomy, and that country affects only currency/localisation. The only minor gap is that the description does not enumerate the 29 subject values or the key_stage values, but it explicitly points to the endpoint markdown for the full list, which is a reasonable pointer.

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 Tes teaching resources'), then immediately names the marketplace (tes.com) and the exact return shape (normalized listing facts: title, author, price, rating, downloads). It also explicitly states what it does NOT return (full listing descriptions) and why, which distinguishes it from a generic search tool. Among siblings like tes_resource_detail and tes_school_search, this description makes the tool's scope unmistakable.

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 gives explicit when-to-use guidance: query is optional and can be omitted for pure filter-driven or fully unfiltered browsing, matching Tes's own search API. It also explains the role of each filter parameter (sort mirrors the Sort by dropdown; key_stage and subject mirror the Refine by filters) and clarifies that country controls only currency/localisation, not taxonomy validity. This is unusually complete routing guidance for an agent.

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