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

Adds substantial behavior beyond annotations: it is paid, server-capped at $0.50 default, idempotent because each paid call is persisted by key before sending, runs ~40s of steps, budget can be raised on later calls, and result data carries integrity caveats ('what LinkedIn says, not confirmed employment... never a complete list'). The 'Paid' framing is consistent with readOnlyHint=false and the 'never pays twice' with idempotentHint=true.

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-loaded with 'Paid. Starts a research job...' and every detail is substantive. However, sentences are long and parenthetical-heavy, and the trailing cost sentence ('settled, in flight and unknown are kept apart') reads as grafted-on, hurting scannability.

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?

No output schema exists, so the description carries the burden — and it does: it documents the next_action.code state machine, cost-bucket semantics, budget behavior, result caveats, and the give_company_id recovery path. Complete for a complex, stateful, paid tool.

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?

Adds meaning beyond the 67%-coverage schema: max_cost_usd is the user's per-job authorization and raising it later lifts the budget; without workspace the job is located in whichever workspace it started; kind=company_people is explained including fidelity caveats. These are genuine semantics the schema does not provide.

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 ('Starts a research job, or resumes the one with this request_id') and clarifies it is the paid, stateful entry point, distinct from siblings like get_research_job and cancel_research_job. An agent can identify it without opening the 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 explicit when-to-call guidance: reuse the same request_id to resume without paying twice, and call again per next_action.code (call_again, wait_until, give_company_id, raise_budget). It doesn't explicitly name sibling alternatives (e.g. get_research_job for status), so just short of a 5.

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