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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, but the description adds real behavioral facts beyond them: a 500-candidate scan ceiling, a 20-record return ceiling, no corpus totals, no paid provider calls, and no documentation hydration. It stops short of explaining ranking or ordering of the returned preview records, which matters for a capped preview.

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?

Three tight sentences, front-loaded with the fast/preview trade-off, then the numeric ceilings, then the routing advice. No filler or restatement of the title, and each clause carries distinct information.

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 and the input schema carries rich per-parameter descriptions, so the description's remaining job is setting expectations about exhaustiveness and cost, which it does well. The one gap is that it never clarifies the overlap with search_llms_registry or explains why full_search_url is not exposed as a sibling tool.

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?

With nine parameters at roughly 67% schema coverage, the schema already documents enums, country patterns and section keys in detail, and the description adds nothing parameter-specific. The only connective tissue is the '20 returned records' note, which implicitly maps to the limit maximum of 20. Baseline 3 is appropriate.

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 establishes that this is a keyword search over a stored index run in a 'fast, non-exhaustive preview' mode, with hard caps on candidates (500) and returned records (20). The verb is somewhat implicit ('stored keyword preview' rather than 'search the index'), and the named alternative 'full_search_url' is not one of the sibling tools (search_llms_registry is), so the differentiation is only partly actionable.

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?

It gives an explicit when-not-to-use rule: go to full_search_url when you need complete results and exact totals. It also implies when to use this (quick, cheap lookups). The guidance loses a point because the recommended alternative is not in the visible sibling set, leaving the agent unclear whether search_llms_registry serves that role.

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