compare

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

Annotations already declare readOnlyHint=true; the description adds genuinely non-structured context — the auth/key requirement and the default pair of runs. It still doesn't clarify what happens if fewer than two runs exist or whether runs must be from the same profile, which are the practical failure modes for a diff tool.

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?

One sentence front-loads the operation and its output, followed by the default and the auth prerequisite. No filler, no repetition of the name, and every clause carries information the agent needs.

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?

With an output schema present, the description need not explain return values, and it covers defaults and the key requirement. The only gap is edge-case behavior — what happens with fewer than two runs or mismatched run origins — which keeps it from being fully complete.

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%, with a/b already documented as older/newer run paths and profile pointing at list_profiles. The description's 'two latest defaults' reinforces the a/b ordering but adds no syntax, format, or constraint detail beyond the schema, so baseline 3 applies.

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 (compare) and resource (two runs of the same instance), and even names what the result contains: new, resolved and persisting findings plus grade change. That output framing separates it cleanly from siblings like history (which lists runs) and get_finding (which retrieves one).

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 default (the two latest runs) and an explicit prerequisite (the user's free key via codedb-lens register), so an agent knows how to call it with minimal input. It does not name alternatives or say when not to use it, e.g. when the user only needs a single run's findings.

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