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

The readOnlyHint annotation already covers the read-only nature, and the description adds the useful prerequisite 'Requires project context.' It does not mention rate limits or auth, but for a read-only comparison tool with the annotation present, this is sufficient and non-contradictory.

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 four sentences, each carrying essential information: the core action, the default behavior, the detail modes, and the relationship to the sibling tool. It is front-loaded with the main purpose and contains no redundant or filler content.

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?

Given four parameters and no output schema, the description covers all necessary decision points: how to choose source and target versions, how to control output size, the requirement for project context, and the alternative tool for a written summary. An agent has enough information to call it correctly.

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% (all four parameters have descriptions). The description reinforces the semantics of sourceVersionId (omit for latest) and detail ('full' vs 'flags') and adds the rationale that 'flags' is 'much smaller, and enough to decide where to look,' which goes beyond the schema text.

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 clearly states the specific verb 'Compare two specification versions' and the resource ('specification versions'), and enumerates the kinds of differences shown (added/removed/modified endpoints and schemas). It also distinguishes itself from the sibling generate_changelog, making its purpose unambiguous.

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 guidance: 'Use this for the raw structural difference' and contrasts it with generate_changelog for a written summary. It also explains how to omit sourceVersionId for the latest published version and describes the two detail modes with their trade-offs, leaving no ambiguity about when to invoke this tool.

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