run_prospect_research

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

Annotations only say it is a non-read-only, open-world, non-idempotent operation. The description adds the economically important behavior annotations cannot express: it spends OpenAI and web search credits, it is rate/limit gated by daily run and dollar caps, and the unconfirmed call is a dry-run preview that reports estimated cost and today's usage.

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?

Four short sentences, front-loaded with the cost warning and the confirm/preview distinction before the parameter notes. No filler, and the ordering matches the order an agent needs the information.

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 credit-spending mutation tool with no output schema and no destructive/rollback annotations, the description covers the critical unknowns (cost, caps, preview mode, consent gate). It stops short of saying what a successful confirmed run returns or whether execution is synchronous, which an agent may still want to know. No contradiction with the annotations (readOnlyHint=false matches a run that spends credits).

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 0% (bare titles only), so the description carries the full burden and does so: it defines confirm's semantics as a gating switch with a real-world consent precondition, and defines client as the domain/slug whose ICP the prospect is scored against, with an example (gong.io). Only domain is left to inference, which is minor.

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?

The description gives a specific verb+resource ('Start a new prospect research run') and immediately clarifies its two modes (preview vs. confirmed run), so the agent knows exactly what the tool does. It does not explicitly name or contrast any of the sibling tools (e.g. list_runs, rank_prospects), so it lands at 4 rather than 5.

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?

Explicit when-to-use and when-not-to-use guidance: 'Without confirm it only returns a preview' and 'Pass confirm=true only after the user agrees.' The agent is given a clear sequencing rule (preview first, confirm after user consent) rather than having to infer it.

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