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

Goes beyond the annotations by disclosing that content is preserved and only positions change, and — importantly — that the reorder is refused if the page changed since lastVersion was read, revealing optimistic concurrency behavior not encoded anywhere else. The destructiveHint=true annotation is implicitly contextualized rather than contradicted; only the response/error shape is left unexplained.

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?

Three tight sentences, front-loaded with the action, followed by the input contract and the failure condition. No filler and no redundancy.

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?

For a mutating tool with no output schema and annotations that only declare the safety profile, the description supplies the essential behavioral facts: preserved content, all-or-nothing input list, and version-gated rejection. It stops short of describing the success response or what the agent should do on a version conflict (e.g., re-read via get_page), which would complete the picture.

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%, so baseline would be 3, but the description adds real semantics: orderedSectionIds must cover every existing section exactly once (schema says this too, but the description reinforces it prominently), and lastVersion is explained as the freshness guard whose staleness causes rejection. That last point materially extends the schema's terse 'current revision version'.

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 ('Reorder the sections on a page') and immediately clarifies that only positions change, which cleanly separates it from insert_section, remove_section, and save_section_content. An agent can distinguish it from siblings without opening a schema.

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 the key usage constraint ('Provide the full ordered list of section IDs — every existing section must be included exactly once') and the precondition that lastVersion must be current. It does not explicitly name sibling alternatives for adding/removing sections, but the full-list contract effectively steers an agent away from partial updates.

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