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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds a genuinely non-schema behavior trait: 'FREE', i.e. this call costs no credits, which matters for an agent deciding whether to call it before a paid search. 'Copy values exactly' also signals that values are matched verbatim, a constraint worth knowing. Return shape (list vs. objects) is left unstated.

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 compact segments, front-loaded with the most decision-relevant fact ('FREE'), then the resource, then the three call modes, then the one imperative. The parenthetical taxonomy list is dense but earns its space by telling the agent what vocabulary exists without a trial call.

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, the description carries the return-value burden and does so adequately by describing what each call mode yields. The remaining gap is the concrete shape of the response (flat string list vs. keyed objects) and any pagination or truncation behavior, which an agent would only discover at call time.

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 100%, so the baseline is 3, but the description goes beyond the schema by explaining how the modes combine (bare call → categories, `category` → values, `query` → word lookup) and enumerating the category space an agent will see. It does not clarify `for`/`parent`/`country` scoping logic, which remains schema-only.

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 states the resource concretely — the filter vocabulary accepted by search_people, count_companies and load_companies — and names those siblings, so an agent can tell it is a lookup/enumeration tool rather than a search tool. The wording ('the filters ... accept, and the exact values they take') implies rather than states the return value, which keeps it just short of a 5.

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 explicit, mode-by-mode invocation guidance: no arguments returns the categories, `category` returns that category's values, `query` does a word lookup, plus the operational rule 'Copy values exactly'. It does not explicitly say 'call this before search_people rather than guessing filter strings', so the when-to-use/alternative routing is implied rather than stated.

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