get_branch

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the 'allowed repository' constraint and identifies that it returns a commit SHA. It doesn't describe edge cases (e.g., what happens for an empty repo with no commits, or whether branch refs are fetched locally vs from remote), but with annotations covering the read-only nature, a 3 is fair.

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?

Single sentence, no filler, front-loaded with the purpose. Nothing could be trimmed without losing meaning. Ideal conciseness.

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?

This is a simple read operation on a branch. With no output schema, the description doesn't describe the return format (e.g., is it a plain SHA string or an object?). The 4-parameter complexity, especially hostname vs account distinction, is not addressed. For a relatively simple tool, it's adequate but not complete—missing the return format and param clarifications keep it from scoring higher.

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 only 25% (only 'repository' has a description saying 'owner/name format'). The description does not elaborate on any of the 4 parameters (account, repository, branch, hostname). It doesn't explain what 'account' means, how hostname differs from account, or clarify branch naming conventions beyond the schema's regex. With low schema coverage and no parameter guidance in the description, the agent must infer parameter meaning.

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 'Read the current commit SHA for a branch in an allowed repository' uses a specific verb (Read) and resource (branch's current commit SHA), clearly distinguishing it from sibling tools like get_repository or list_repository_tree. It's clear and specific, though it doesn't explicitly contrast with siblings.

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 mentions 'in an allowed repository' which implies there may be a restriction on which repositories are accessible, providing some context. However, it doesn't explicitly state when to use this vs alternatives like get_repository, get_repository_file, or list_repository_tree, nor does it mention prerequisites like the repository needing to exist or auth being required.

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