verify

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

Discloses that it sets finish_check state after a green run, per-command timeout, and optional allowlist. Annotations indicate idempotentHint and openWorldHint, and description adds context about state mutation without contradicting annotations.

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?

Description is brief but information-dense, front-loading the purpose. The REQUIRED section is well-placed. A slight improvement could be separating usage from prohibition, but overall efficient.

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?

Covers key aspects: what it does, security mode, timeout, allowlist, and required post-processing. However, lacks description of return values or error behavior (no output schema). Given complexity, it's adequate but not complete.

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 88%, so baseline is 3. The description adds minimal extra meaning beyond what's in the schema (e.g., 'argv-mode default' is already in exec_mode description). No major new insights for parameters.

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?

Description clearly states it runs lint/build/test gates and its role as a required step before finish_check. The verb 'run' and resource 'gates' are specific, and it distinguishes itself from siblings by its unique gate-checking function.

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?

Explicitly provides when to use (required before finish_check) and how to handle outcomes (set verify_ran or verify_abstained). Could be improved by comparing to sibling tools or stating when not to use, but current guidance is strong.

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