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

With no annotations, the description carries full responsibility. It discloses offline/no key/no network, specific gates (in-policy, clears finding, no new finding, no network/exec sink, bounded size), non-writing behavior, and agent responsibility. This is thorough and leaves no major behavioral surprises.

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 a single dense paragraph, but every sentence contributes meaningful information. It front-loads the core purpose and avoids fluff. Minor improvement could be splitting into shorter sentences, but it is appropriately sized for the complexity.

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 and lack of output schema, the description covers inputs, process, constraints, and expected output (approved:true). It also tells the agent how to proceed after verification (write only if approved, never auto-merge). This is complete for safe and correct use.

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 coverage is 100%, so baseline 3. The description reinforces that newContent must be the 'FULL corrected content' and adds context about verification gates, but it primarily restates schema field descriptions. It does not add substantial new parameter semantics beyond what the schema already provides.

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's purpose: 'Deterministically VERIFY a proposed fix before writing it' and explicitly contrasts with writing tools by saying 'This does NOT write the file.' It distinguishes itself from siblings like verify_fix and remediate_findings by emphasizing deterministic verification, offline operation, and blast-radius gates.

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 clear context on when to use: when verifying a proposed fix before writing, with inputs (finding, current content, proposed content) and the output (approved:true). It implicitly differentiates from apply_triage and remediate_findings by stating it never auto-merges and the agent must write manually. However, it does not explicitly name alternative tools or exclusion criteria.

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