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

Annotations already declare readOnlyHint/idempotent/destructive=false; the description adds valuable behavior: it is free, nothing is reserved or sent, and it runs against live provider schemas. It stops short of rate limits or latency, so not a full 5.

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?

Front-loads the key fact (Free / nothing reserved) and packs useful detail efficiently. Some clauses are dense run-ons, but every sentence carries meaning without bloat.

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 a 4-param nested tool with no output schema, it conveys purpose, cost semantics, and the handoff to start_research_job well enough to call correctly. It doesn't sketch the estimate's return shape beyond at_most_usd, a minor gap.

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 50%, but the description compensates by explaining kind company_people semantics ('who LinkedIn lists with a current role… by title and place if given') and the company-vs-company_id lookup rule (taken only when exactly one company matches). max_results and workspace are left to 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+resource: it tells what a research job would do and its maximum cost, drawn from live provider schemas, with nothing reserved or sent. It clearly distinguishes itself from start_research_job, the actual job-starting sibling it feeds into.

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 clearly frames this as the free preview step whose at_most_usd feeds start_research_job's max_cost_usd, giving the agent an explicit path to the alternative. It doesn't explicitly state when-not-to-use (e.g. once a job exists), but the context is clear.

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