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

Annotations already cover read-only/idempotent/closed-world, but the description adds substantive context the annotations cannot: results are full provenanced vendor records, each plan carries source url + accessedAt, and each priced plan includes a one-line `citation`. What it omits is result-count limits, pagination, and ranking order for a query that could return the whole theme.

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?

Purpose is front-loaded in the opening clause and each sentence adds a distinct fact (scope, section routing, return provenance, empty-query behavior). The middle sentence about citations is a dense run-on that could be tightened, but nothing is truly wasted.

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 and only 2 optional parameters, the description covers what an agent needs: corpus, section routing, empty-query fallback, and the shape of returned records including provenance. Missing result-limit/pagination and match-ordering details keep it just short of complete.

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 only 50% (the `query` param has no schema description), and the description compensates well by naming the searchable fields, giving multi-token example queries ('hipaa restaurant', 'google ads zapier'), and defining empty-query behavior. It does not state whether multiple terms are ANDed or how matches are scored, so token-combination semantics remain inferred.

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+resource ('Search any theme's data index') and enumerates the searchable fields (vendor name, domain, integrations, plan notes, capabilities), so an agent knows exactly what corpus is being hit. It never mentions the sibling search_products or explains the vendor-vs-product split, which is the one distinction an agent most needs given 275 pricing topics.

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?

Clear operating context: applies to every theme, both hub sections and catalog topics, with an explicit pointer to list_sections for the slug and to the `section` parameter. The 'empty query returns all vendors' note is useful behavioral guidance. It stops short of naming alternatives or exclusions (e.g., when to prefer search_products or find_best).

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