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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real value by stating no AI calls or data refreshes occur, which is the key behavioral guarantee for a replay. It does not, however, say anything about how results are reported or how long a replay takes.

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?

Two short, front-loaded sentences with no filler; the guarantee about AI and refresh is placed immediately after the purpose statement. It is efficient, though the purpose is expressed as a noun phrase rather than a direct verb+object statement.

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?

An output schema exists, so return values need not be explained, but the description leaves gaps for a two-required-ID tool: it does not say what a replay compares, what a passing versus failing verification looks like, or how to obtain the report and project identifiers.

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 0% and neither project_id nor report_id is described in the schema or the description. The description never mentions the two required identifiers or where they come from, so it fails to compensate for the coverage gap.

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 names a concrete operation on a concrete resource: it verifies a frozen research report by replaying inputs, checking deterministic results and report text. This distinguishes it from retrieval siblings such as research_get_report or research_explore_report, although it stops short of naming them explicitly.

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 clause 'Never calls AI or refreshes data' implies this is the tool to pick when an offline, reproducible check is wanted rather than a live refresh, but there is no explicit when-to-use or when-not-to-use instruction and no named alternative.

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