List Patronus Runs

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

With no annotations, the description must carry the full burden for behavioral transparency. It discloses the output format (YAML list) and that runs are dry runs/safe merges, but does not explicitly state read-only behavior, permission needs, rate limits, or any side effects. This leaves some uncertainty for an agent, but the core purpose and return type are conveyed.

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 concise and well-structured: a brief purpose statement, usage context, follow-up note, and clearly labeled Args/Returns sections. Every sentence contributes value, and the format is easy to parse, making it efficient for an agent.

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 simple list tool with two parameters and an output schema, the description is complete. It provides examples for both parameters, states the return type (YAML list), and explains how the results are used with get_patronus_run. No critical information appears missing, given the tool's simplicity.

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 schema has 0% coverage, so the description compensates by explaining both parameters: project is a project key with example 'ij', and review_id is an MR number with example '194108'. These concrete examples and definitions add substantial meaning beyond the bare schema, though more nuance (e.g., where to find the project key) could improve usefulness.

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 finds/lists Patronus runs (dry runs / safe merges) for a merge request, using the specific verb 'Find' and identifying the resource. It differentiates from the sibling get_patronus_run by noting each run's ID can be passed to that tool for follow-up queries, establishing distinct scope.

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 says 'Use this to discover CI dry runs and safe merge attempts for a merge request,' providing a clear context for usage. It implicitly distinguishes from get_patronus_run by pointing to that tool for individual run details, though it doesn't explicitly state exclusions for cases where a run ID is already known.

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