compare_documents

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

With no annotations, the description carries the full burden and does well: it states the tool writes nothing, discloses the limitation that only free body paragraphs are covered in the first version, and specifies failure behavior (unsupported changes set isComplete false and plan null). It stops short of permission/auth or performance details, but the mutation and failure semantics are clearly conveyed.

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?

Four tight sentences, front-loaded with the core action and outputs before the caveats. Every sentence adds information (returned fields, coverage scope, failure mode, write semantics); no wasted filler.

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 no output schema, the description usefully describes the return payload (differences, hashes, diagnostics, plan) and the isComplete/plan-null contract. The remaining gap is parameter-level meaning for five required, undocumented inputs, but the overall behavioral picture is complete enough to invoke the tool.

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?

All five parameters are required with 0% schema description coverage, so the description must compensate and largely does not. It conveys an original/revised pairing and 'bound to the original snapshot,' and mentions revisionAuthor only obliquely, but never explains the connectionId vs. documentId distinction or the role of each parameter.

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 opens with a specific verb (read/compare) and resource (two Word documents) and enumerates the outputs: paragraph differences, SHA-256 hashes, coverage diagnostics, and a tracked-change plan. It distinguishes itself as a non-writing producer of a plan, though it never names a sibling tool explicitly (e.g., preview_document_merge) to sharpen the contrast.

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?

Workflow guidance is implied by 'This tool writes nothing; preview and apply the returned plan against the original document,' which situates it before preview_plan/apply_plan. However, it gives no explicit when-to-use vs. when-not criteria or named alternative for comparison/merge scenarios.

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