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

Goes well beyond the readOnlyHint=false annotation: it describes the job as asynchronous and bounded, defines the return envelope {audit_id, status, result?}, discloses caching behavior, and explains that for the caller's own company the count comes from the ledger and includes case ids. The mutation implied by readOnlyHint=false (creating a persistent audit job) is consistent with the returned audit_id.

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?

Purpose and return shape are front-loaded and nothing is redundant, but several sentences are long multi-clause runs (the results-and-plans sentence in particular) that take effort to parse on a first read.

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?

With no output schema and no annotation detail, the description still supplies everything needed to call and follow up correctly: input scope, async status handling, polling target, return envelope, UI-facing instructions for result.summary and result.next_step, and the cache/ledger exceptions.

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?

The single 'domain' parameter has 0% schema description coverage, so the description must carry it and only partially does: 'any public Trustpilot business domain' implies a domain string rather than a full URL or a business id, but format, normalization, and accepted variants are never spelled out.

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 and resource ('audit any public Trustpilot business domain') plus precise scope: reads the profile and low-star reviews, counts likely-disputable ones per category, and never returns review text. That last clause cleanly separates it from siblings like list_disputable_reviews and list_review_triage, which presumably surface text.

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 routing conditions: while status is running, poll get_audit_result; when result.next_step is non-null, direct the user to get_checkout_link for the chosen plan, or to request access while billing is off. It also flags that a repeat audit inside the cache window returns the cached result, so an agent knows not to expect a fresh run.

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