Compare Step Versions

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

Beyond the readOnly/idempotent annotations, it discloses what is returned (deltas expressed in the baseline's declared unit, PMI counts, document facts) and adds interpretive caveats the annotations cannot carry: PMI counts show presence of callouts, not whether any is satisfied, and file-level facts do not explain design intent. That is real behavioral context an agent needs to avoid misreporting results.

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 core action and accepted input forms come first, then the return contents, then the interpretation caveats. Four dense sentences, each adding a distinct fact, with no redundant restatement of the name or schema.

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 and both parameters documented, the description covers the remaining gaps: unit conventions for deltas, what is and isn't included in PMI counts, and the scope limit of the comparison. Nothing needed to call it correctly is absent.

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% and already documents that each uri is a file: URI or absolute path, so the description's repeat of that phrasing adds little. Baseline 3 applies since the schema carries the parameter burden.

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 and resource ('Compare baseline and candidate STEP artifacts') plus the accepted input forms. The comparison framing clearly separates it from siblings like inspect, measure, and describe_pmi, which operate on a single artifact.

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 comparison intent implies when to use it, but the description never explicitly routes the agent: it doesn't say to use diff instead of running inspect twice, or state prerequisites (same unit system, both files must exist). Usage is inferable but not spelled out.

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