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

Annotations already mark this as readOnly, idempotent, and non-destructive. The description adds valuable behavioral context beyond that: stale editions have null hashes and an approval prohibition, and the operations should not be paraphrased as approved text. This materially changes how an agent should interpret and use the result.

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?

Two sentences with no wasteful filler, and the most important framing ('One proposed page change') comes first. The first sentence is dense and lists many required fields, but each element earns its place because it tells the agent what to expect in the payload.

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?

The output schema exists, so return-value details are already structured. Annotations cover the read-only and non-destructive safety profile. The description supplies the remaining operational context: when to read this, what cannot be approved, and how the content should be presented to the customer. Nothing essential is missing.

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?

The schema has one required parameter, jobId, with a uuid format and 0% description coverage. The description never mentions jobId explicitly, but it does clarify what the job object refers to ('One proposed page change'), which indirectly clarifies what the id identifies. A single obvious uuid parameter makes this adequate, though a mention would have been stronger.

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 states exactly what the tool does: it reads a single proposed page change in full — rationale, brief, objectives, drafted operations with before/after values and canonical hash, and `fix` status. This precise verb+resource pairing distinguishes it from related tools like get_approved_change, which would return an already-approved change.

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 gives explicit workflow guidance: 'Read this with the customer before approve_change; never paraphrase the operations as approved text.' It also tells the agent when not to treat the result as approvable via the stale-edition clause ('A stale edition is readable history with a null hash; it can never be approved').

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