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

Annotations already declare destructiveHint=true, but the description adds crucial behavioral context: the anonymization requirement ('no names, amounts, or PII'), the fact that reviews are a paid engagement ('never describe it as free'), the queuing behavior ('nothing reaches an accountant until the user engages'), and the one-call limit. This far exceeds what annotations convey and provides actionable behavioral rules.

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 description is dense but every sentence earns its place. It front-loads the core purpose and the single-channel constraint, then structures two modes with clear prerequisites. The caveats (anonymization, paid engagement, manual queue, call limits) are packed efficiently without fluff. For a tool with 9 parameters and two complex modes, this is remarkably concise.

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?

Given the tool's complexity—two modes, conditional parameters, potential legal/ethical implications—the description covers all necessary aspects: what triggers it, how each mode works, required parameters, behavioral constraints, and even notes about the output (booking link). The output schema exists, so return format is covered, and the description is sufficient for correct invocation without relying on external knowledge.

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?

While schema coverage is 100%, the description adds significant semantic value by explaining the interaction between parameters: how request_review toggles the mode, the conditional requirement for contact_email, the completeness expectation for working_paper, and the anonymization constraint on note. It also clarifies that skill_slug is for skill-specific feedback and replaces old submit_feedback. This goes well beyond the schema's per-parameter 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?

The description states a clear verb and resource: 'Sends feedback or a review request to OpenAccountants.' It also explicitly declares itself 'the single outbound channel,' distinguishing it from the read-only sibling tools. The two modes are clearly outlined, leaving no ambiguity about what the tool does.

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?

Provides explicit when-to-use and when-not-to-use guidance: 'does nothing unless the user has explicitly asked,' 'Call at most once per explicit user request; never call as a routine closing step, and never solicit the request.' It also specifies the conditions for each mode, such as requiring working_paper, jurisdiction, scenario, and contact_email for request_review. This is comprehensive routing guidance.

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