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

Annotations already cover read-only/idempotent/no-destruction, and the description adds genuinely new behavioral context: pagination depth (up to 500,000 pages), page size bounds (10–100), and a cost model (2 points per returned record) that matters for a 71-filter search. It does not say whether filters are ANDed or what an empty filter set returns, which is the remaining behavioral gap.

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 front-loaded sentences covering filters, return fields, and paging/cost — high information density with no filler. The paging clause ('paged up to 500,000 pages of 10–100 leads') is slightly compressed but still readable.

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 an all-optional, 71-parameter search with no output schema, the description covers the input surface and substitutes for a return schema by naming the fields returned plus cost and paging. Only the combination semantics of filters and the size of an unfiltered result are 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 description coverage is 100%, so the schema already documents all 71 parameters with examples. The description only groups them into families and adds page_size/page bounds, so baseline 3 applies — it adds structure but no meaning beyond the schema.

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 and resource ('Find leads') and enumerates the filter families (person, location, company, industry, tech stack, funding, traffic, hiring, HQ), so the agent knows it is a people/lead search rather than a company search. It does not name the nearest siblings (run_linkedin_people_search, run_company_employees), so the boundary is left to inference.

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?

'optionally within one company' hints at a scoping mode, implying you can run broad or narrow, but there is no explicit when-to-use or when-not guidance and no named alternative. Usage is only weakly implied by the filter list.

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