get_branches

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

Discloses that the response can be large and that limit should be used. No annotations exist, so the description carries full burden. It does not mention permissions, scope, or side effects. For a read-only tool, this is acceptable but could be more explicit about behavior.

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, front-loaded with purpose and critical note, and structured with clear Args and Returns sections. Every sentence adds value without redundancy.

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 purpose, parameters, and return type (BranchesOut with names and hashes). Given the tool's simplicity and the presence of an output schema, the description is mostly complete. Lacks details on error handling or ordering, but these are not critical for a basic list 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?

Schema description coverage is 0%, so the description must compensate. It explains that 'name' is a substring match, 'user' filters by user, and 'limit' is a maximum with default 10. This adds significant meaning beyond the schema's type definitions.

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 'Retrieve branches from the user's Bauplan data catalog as a list', specifying the resource (branches) and action (retrieve/list). Distinguishes from siblings like create_branch and delete_branch by being a read operation.

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?

Provides a strong usage guideline: 'NOTE: This can return a large response. Always use limit parameter.' This advises on when to use and how to avoid issues. However, it does not explicitly mention alternative tools (e.g., has_branch) or when not to use.

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