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

Beyond annotations, the description discloses that this is a write-tier tool, may require manager approval, has default dry-run behavior, and can file up to 5 bug cards when file_top_n is set. It also explains approval nuances and instructs the agent not to re-ask in chat after the card is created. No contradiction with readOnlyHint=false or destructiveHint=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?

The core purpose is front-loaded in the first sentence, and the routing and approval notes are valuable. However, the description is dense and repeats some dry-run/file_top_n concepts between the first paragraph and the routing section, and the approval bracket is longer than strictly necessary for an agent to invoke the tool correctly.

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 tool with no output schema, the description covers purpose, when to use, required membership, approval behavior, and a full end-to-end routing workflow. The main gap is that the return shape of the ranked candidates is only loosely described as 'ranked product-request candidates,' and the duplicate companyId/company_id parameters are not disambiguated, but the essentials for correct invocation are present.

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 parameters. The description adds some reinforcement around dry-run behavior and file_top_n's max of 5, but it does not add meaningfully new semantics for lookback_days or resolve the companyId/company_id ambiguity present in the schema. With full schema coverage, the baseline of 3 is appropriate.

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 states a specific action and deliverable: scan a company for product-system bugs/unlocks and return ranked product-request candidates. It also names the exact bug/unlock categories and explicitly excludes feature fantasy, making the tool's scope unambiguous and distinct from follow-up tools like claim_product_request_for_builder.

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 gives an explicit trigger ('Use when the product team is hunting class bugs/unlocks across a portfolio tenant'), a required membership condition, and a step-by-step routing workflow: dry-run first, review, re-run with file_top_n=1..3, then claim. It also clarifies when not to use it (does not invent feature fantasy).

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