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

The annotations include readOnlyHint=false and destructiveHint=false, but the description goes beyond them by explaining the tool's mutating nature (submitting data) and the need for consent. It also discloses potential failure modes: 'no_response' meaning the service didn't answer in time retry, and field-specific errors requiring user correction and resubmission. This adds behavioral context beyond the annotations, though it doesn't mention rate limits or side effects like sending emails to the user.

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 well-structured: it starts with the core purpose, then prerequisites (confirmation), then handling results. It is reasonably concise for the amount of guidance it provides, but it could be more front-loaded by putting the core action first (which it does) and then the conditions. It's not overly verbose; each sentence adds value.

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 (13 parameters, requirement for consent, and multiple failure modes), the description covers the essential usage: how to handle consent, exact option values, and error handling. It doesn't explain the output schema in the description, but since an output schema exists, it doesn't need to. It also could mention that it's for the free service only, but that's in the description. Overall, it is complete for an agent to call correctly.

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 46%, so the description compensates by providing key parameter semantics: it explains consent must be true and set only after confirmation, and mentions using exact option values from get_matching_questions for certain fields (though not explicitly listing them). It also clarifies the meaning of address for buyers vs sellers. However, not all 13 parameters are covered; some like notes and quiz_version lack description guidance, but the schema does describe some.

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 clearly states the tool submits the user's questionnaire and contact details to the matching service. It identifies the resource (Rate-My-Agent.com's free agent-matching service) and the verb (submits). It differentiates from siblings by focusing on the submission action, while get_matching_questions is for fetching questions and get_local_agent_review_data for reviews. However, it could be more specific about the expected outcome (a match result) rather than just registration.

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 guidance: only after showing the user their answers and receiving explicit confirmation. It also details when not to use immediately (must confirm first) and specifies the consent parameter to record that confirmation. The description also gives post-submission handling instructions, which effectively tells the agent what to do after invoking the tool, making usage clear beyond just selection.

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