Start background static checks

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

Discloses fire-and-forget nature, no blocking, CPU-bound, file output, and survival after call. Annotations already indicate non-readOnly, so description adds context like resource usage and persistence.

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?

Well-structured, front-loaded with core action. Slightly verbose but each sentence adds value. Could be trimmed slightly for conciseness.

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 return value, failure case, file location, and polling mechanism. No output schema needed as descriptions handles it. Complete for a fire-and-forget tool.

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?

Description explains revision defaults and ticket association beyond schema descriptions. Project parameter not described in schema, but description implies its role.

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?

Clearly states it spawns a detached background run of static checks on project's .js/.mjs/.cjs files and returns a runId. Distinguishes from sibling commit_feature which does automatic checks.

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 says 'use this to run them on demand' and notes commit_feature auto-starts checks. Also explains when it returns started:false (no config).

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