Recipe source files

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

Annotations only declare readOnly/idempotent/openWorld, but the description adds substantial non-obvious behavior: files are read from the default branch head, files over 512 KB or containing secret-shaped content return content null, and stale shas cause refusal at propose time. This is exactly the kind of behavioral context annotations cannot carry.

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?

Front-loaded with purpose, then behavior, then return shape and the read-only note; nearly every clause earns its place. The parenthetical enumerations of element values duplicate the schema, which is the only minor 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?

There is no output schema, yet the description fully specifies the return envelope ({ ok, element, branch, headSha, files } or { ok: false, reason }) and the per-file fields { path, exists, content, sha, writable, reason }. Nothing an agent needs to call and interpret this tool is missing.

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 both parameters are already documented in the schema, and the description largely repeats the enum semantics verbatim. It adds only 'Optional projectId', which the schema already conveys via the description and non-required status. Baseline 3 is appropriate.

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?

States a specific verb+resource with scope: 'Return the repo files a recipe change may edit for one part of the recipe', then enumerates the three element variants. An agent can distinguish this from siblings like get_app_recipe, get_recipe_change, and propose_recipe_change without opening a schema.

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?

Gives a concrete workflow instruction: 'Pass each sha as baseSha to propose_recipe_change so a file that changed since is refused', which tells the agent this tool feeds the propose workflow. It does not state when NOT to use it or name alternative sources of similar info (e.g. get_app_recipe), so it falls short of a 5.

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