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

Goes well beyond the readOnly/openWorld annotations: it discloses the 10-result cap, the 1000-rows-per-day account allowance, the exact nextCursor pagination rule (same filters), and a prompt-injection warning that result names/headlines are untrusted third-party text. These are precisely the operational facts an agent cannot get from annotations or schema.

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?

Dense but front-loaded, with the most decision-relevant facts (its own-account scope, filters, alternatives) in the first sentences. The bracketed 'Ids in/Ids out' prefix is a terse custom notation that costs a little clarity without much payoff, keeping this just short of ideal.

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-shape burden and does so (name, headline, location, profile URL, degree) plus pagination, rate limits, and untrusted-data handling. Nothing an agent needs to invoke this 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 100%, so the baseline is 3. The description still adds interpretive meaning beyond the schema: keywords cover name/title/company/any words, location is a city/region/country name, network maps to first/second/third degree, and cursor requires unchanged filters. This meaningfully improves on the raw schema descriptions.

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 people with LinkedIn's ordinary people search') and pins its identity by contrasting with Sales Navigator ('no Sales Navigator seat needed and no credits'). It also names the field set returned, so the agent knows exactly what this tool is for versus the many other search_* siblings.

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 concrete context (filters supported: keywords, location, network) and routes 'every other LinkedIn filter' to search_linkedin, plus pagination instructions. It does not explicitly disambiguate from the nearest people-search siblings like search_linkedin_people or search_linkedin_sales_navigator_people, so guidance is strong but not exhaustive.

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