compare-pages

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

The description goes beyond annotations by detailing additional behaviors: text-vs-text is rejected, only changes are returned, truncation at 50000 bytes, and the effect of includeDiff=false. Annotations already declare readOnlyHint and idempotentHint, so the bar for transparency is partially met; the description adds useful but not exhaustive context (e.g., no mention of response format details).

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 a single paragraph of about 120 words. It covers all key points without excessive verbosity. However, it could be slightly more structured (e.g., bullet points for options) to improve scannability, but it is efficient and front-loaded with the core purpose.

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 no output schema, the description adequately explains what the tool returns (diff, change flag, metadata, size delta) and how truncation works. It also references a sibling (get-page) for full text. It covers the main use cases and limitations, though a bit more detail on response structure would improve completeness.

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 7 parameters have schema descriptions, so baseline is 3. The description adds value by explaining the side-acceptance rules (revision ID, title, or text but not both sides as text) and the special behavior of includeDiff. This clarifies constraints and options beyond the schema's simple type/description.

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 tool returns changes between two versions of a wiki page as a compact text diff. It specifies what each side accepts and rejects, and distinguishes itself from get-page by noting it only returns changes. The verb 'returns' and resource 'changes' are specific and 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 explicitly tells when to use this tool (to get diffs) and when to use an alternative (get-page for full text). It also explains the includeDiff=false option for cheap change-detection, and notes error cases (nonexistent title/revision). This provides clear guidance on tool selection and usage.

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