Start Patronus Dry Run

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

No annotations are present, so the description itself carries the burden. It discloses that this is a non-destructive operation ('without merging') and describes the return behavior: Markdown with run ID, URL, and status, plus failure guidance. This gives the agent reasonable expectation of side effects and output, though it does not mention async timing or requirements like accessible MR.

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 well-structured with a summary, behavior, args, and returns sections. Every line adds value: the args examples are useful, and the return description is necessary. It's slightly longer than minimal but not bloated.

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?

With only two string parameters and no annotations, the description provides enough context for invocation. It includes return value details and points to get_patronus_run for follow-up. It doesn't cover edge cases like duplicate runs or permissions, but for a simple start command it's sufficiently 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?

The input schema provides only types and required flags, with 0% description coverage. The description's Args section supplies semantic meaning: 'project' is a project key (e.g., 'ij') and 'review_id' is an MR number (e.g., '194108'). These examples help the agent generate correct values, though it doesn't specify exact regex/format constraints.

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 verb 'Start' and the resource 'Patronus dry run for a merge request'. It distinguishes itself from siblings like get_patronus_run and post_cancel_patronus_run by focusing on initiation. The phrase 'Runs all configured quality checks (TeamCity builds) without merging' adds specificity.

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 explains what the tool does ('Runs all configured quality checks... without merging'), which implicitly tells when to use it. It explicitly points to the sibling get_patronus_run for tracking progress, providing an alternative. It does not explicitly list when not to use, but the guidance is sufficient for selection.

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