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

With no annotations, the description carries the full burden and it succeeds richly. It discloses return values like ahead_by, behind_by, and status; explains the diverged state and its relation to a 409 conflict; clarifies that files[] lists differences rather than conflicts; and warns about deploy-generated data in solution.json and skills files.

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 longer than average but every sentence earns its place: the first line is a bold, scannable summary followed by structured bullets and a brief important note about deploy-generated data. It is front-loaded with the core comparison behavior and the promote tie-in, so an agent gets the key message immediately.

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 read-only diff tool with no output schema and no annotations, this description is nearly complete. It covers defaults, when to use, how to interpret return values, failure diagnosis, and known data quirks. The only minor omissions are general edge cases around invalid refs, but those are not critical given how much is already disclosed.

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 coverage is 100%, so baseline is 3. The description adds meaningful conceptual value beyond the schema by explaining that base/head can be overridden with arbitrary branches, tags, or commits, and by framing base as the target and head as the source in the promote workflow. It doesn't add much per-parameter syntax detail, but the added framing is useful.

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 uses a specific verb ('Compares') with a clear resource and scope: dev vs main by default, showing exactly which commits and files ship with a promote. It explicitly orients the agent as a pre-flight check for ateam_github_promote, which clearly distinguishes it from the many sibling GitHub tools.

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 provides explicit when-to-use bullets: before promoting, to check if dev is ahead, to diagnose a failed promote, and for arbitrary branch comparisons. It even instructs the agent to ALWAYS call this after a promote failure before reporting to the user, which is strong, actionable usage guidance.

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