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

With no annotations, the description carries the full burden and does so well: it discloses the multi-step workflow (branch creation, commit, PR open), the branch naming convention (eco/…), the human-in-the-loop review requirement, and a meaningful safety property (never writes to an existing branch). It leaves out auth/permission specifics and failure behavior, which keeps it short of a 5.

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?

A single dense sentence (with a colonic elaboration) that front-loads the outcome and packs the workflow without a wasted clause. Nothing restates the title or the field names redundantly.

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 mutation-style tool with no annotations and no output schema, the description supplies the workflow, the safety guarantee, and the review semantics an agent needs to invoke it correctly. Missing only operational details like permission scope or error handling, which are not strictly required to call it.

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 schema already documents every parameter, making 3 the baseline. The description reinforces that 'files' means full new content per file and ties them to the commit step, but adds no syntax, format, or constraint detail beyond what the schema already provides.

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 (propose a change), resource (GitHub repository), and mechanism (pull request), then clarifies exactly how it differs from a generic write: new branch, commit, open PR for human review. An agent can distinguish this from github_read, github_search, and github_create_issue without opening any 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?

Clearly signals the intended context (proposing changes for human review rather than direct writes) and includes a scope constraint ('Never writes to an existing branch') that tells the agent when this tool is and is not appropriate. It stops short of naming explicit alternatives or a when-not condition beyond that constraint.

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