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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, yet the description still adds real operational context: quota consumption per returned row, pagination via next_cursor, and the exclusion of the tool's own maker from team_uses counts. That is genuine value beyond the structured fields, though the exact consequences of exhausting quota are not spelled out.

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 and the workflow tail is well placed, but the description re-enumerates the filter list and repeats the per-company quota cost that the limit parameter already states. Two sentences duplicate structured data that the agent will read anyway.

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 supplies the return shape (one row per company with the named fields), the cost model, the paging contract, and the downstream workflow. Nothing needed to invoke it correctly is missing.

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 already 100%, so the baseline is 3; the description earns above that by explaining the semantics behind team_uses (internal tools derived from current employees' skills, minimum two users, maker excluded) and researching (buyer intent from recent reading), which the schema only names in passing. It does not add format or range guidance beyond what the filters property already documents.

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?

Opens with a specific verb and resource ("Find companies") and enumerates the qualifying dimensions, then explicitly scopes it as "without people," which cleanly separates it from person_search. An agent can distinguish this from every sibling without opening a schema.

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?

Gives a concrete workflow: start with a small limit, page with next_cursor, then follow with person_search using the same filters or domains, or company_signals for a single account. Both the when-to-use and the named alternatives are stated outright.

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