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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful behavioral context beyond annotations: the tool may return `not_implemented` until old object versions are retained, and the agent should tell the user. It still omits return/pagination details, but for a diff tool the failure caveat is substantial.

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?

Two sentences, front-loaded with the operation and immediately followed by the operational caveat. No filler or repetition beyond the title phrase.

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 annotations covering safety, the description supplies the core purpose and a critical backend limitation. Since there is no output schema, it could say more about the returned diff format or reachable paths, but the detailed path schema already carries permission and layout constraints.

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 50%; `path` and `project_key` are documented in the schema, but `from` and `to` rely mostly on their regex patterns. The description adds that the operation compares two commits and that `to` defaults to current, but it does not explain the commit-hash semantics or required/optional distinction beyond that.

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 operation—producing a unified diff—for a single path between two commits, and notes that `to` defaults to current. This is clear enough to distinguish from read/list/history siblings, though it does not name `get_history` or any alternative explicitly.

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 implies use when comparing a path across commits and gives an important fallback instruction if the backend returns `not_implemented`. It does not say when to choose this over `get_history`, `read_file`, or other siblings, nor does it list prerequisites or exclusions.

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