start_validation

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

With no annotations provided, the description carries the behavioral disclosure burden. It does well by revealing that the job runs in the background, that progress is polled via get_validation_status, and that results are written to codeguardian-report.json at the project root, explicitly noting it is NOT inside .codeguardian/. It stops short of describing potential overwrite behavior or immediate return values, but the main side effect and output location are disclosed.

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 three sentences with no filler. The first sentence states purpose and threshold, the second gives the most important scoping exception, and the third covers polling and output location. Every sentence earns its place and the most decision-relevant information is front-loaded.

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?

For a background job with no output schema, the description covers the key operational needs: when to use it, how to scope it, how to check progress, and where results land. The main omission is the immediate return value of start_validation itself (e.g., whether it returns a job ID needed for get_validation_status), but the rest of the workflow is well-specified.

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 100%, so the baseline is 3 and the description is not required to add param detail. The monorepo scoping advice in the description partially reinforces projectPath semantics, though it largely duplicates the schema's existing guidance about avoiding the monorepo root. No significant new parameter meaning is added beyond the schema.

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: 'Start a background validation job' for 'large codebases (>50 files)'. It clearly differentiates from siblings by emphasizing the background/asynchronous nature and by pointing to get_validation_status for follow-up, which separates it from synchronous validation or status 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 when-to-use guidance: large codebases over 50 files to avoid timeouts. It also provides concrete monorepo scoping advice and names the polling tool to use afterward. It does not explicitly name validate_code as the alternative for small codebases, but the >50-file threshold makes the intended boundary reasonably clear.

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