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

Annotations already mark destructiveHint=true, but the description adds critical context: the certificate is irreversible and outward-facing, revocable but signature stays cryptographically valid forever, refusals are permanent outcomes not transport errors, and it is classified RED requiring human authorization. This goes far beyond the annotation's basic destructive flag and warns the agent of consequences.

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?

Although lengthy, every sentence earns its place: core purpose, what it does NOT attest, irreversibility warning, RED classification and human-authorization behavior, preconditions, refusal codes with fixes, and tier restriction. It is front-loaded with the action and safety warnings, and feels appropriately dense for such high-stakes functionality.

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 irreversible, outward-facing, and human-gated nature, the description covers all necessary aspects: purpose, limitations, preconditions, error handling, permission model, and access tier. An output schema exists, so return-value details are not required. It is fully self-contained for safe invocation by a governed agent.

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 input schema covers 100% of the only parameter (report_id) with a detailed description, including provenance ('as returned by create_report / list_my_reports / save_freeform_report') and ownership constraint ('Must be authored by the calling customer'). The tool description reiterates that ownership requirement but adds no new parameter-specific semantics, so the baseline 3 applies.

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 opens with a specific verb and resource: 'Request a Valuein compliance certificate for one of the caller's OWN reports.' It precisely defines what is attested (absence of lookahead bias) and distinguishes itself from siblings by stating it attests provenance ONLY, not correctness. This clearly differentiates from publish_report, delete_report, and other report-related tools.

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?

The description gives explicit preconditions ('every figure must already be reviewed via save_figure_review — check with list_figure_reviews first'), permanent refusal handling with named codes, authorization constraint ('Only the report's author may sign it off'), and tier restriction. It also provides when-not guidance: 'must never be presented as though it did [attest correctness]' and 'Do not retry a refusal unchanged.'

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