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

Annotations already mark this as non-read-only, open-world, idempotent, and non-destructive, but the description adds meaningful context: stale/mismatched hashes are refused, approval must come from the customer, and the follow-up path depends on fix.publisherReady. It also discloses the required OAuth/API scope, which is not present in annotations.

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?

Every sentence earns its place: purpose, precondition, failure mode, customer-decision boundary, conditional workflow, and auth requirement. The most important usage condition is front-loaded immediately after the action statement.

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 description covers preconditions, auth, failure behavior, and the exact conditional post-approval workflow, while the output schema handles return-value details. Nothing needed to invoke this tool correctly appears to be 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?

Schema description coverage is 0%, so the description must compensate. It does clarify expectedHash's meaning ('exact canonical hash') and the refusal behavior for stale or mismatched values, but it does not explicitly explain changeSetId beyond the schema's name and UUID format. Still, the phrase 'one drafted change set' anchors changeSetId well enough.

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 names a specific action ('Approve one drafted change set'), a precise identifier ('exact canonical hash'), and clearly separates it from siblings like reject_change and reask_change. It is immediately obvious what the tool does and how it differs from nearby operations.

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?

It states an explicit precondition ('Call this only after the customer has read the operations from get_page_job and told you to approve that hash') and clarifies that approval is the customer's decision, not the agent's. The conditional workflow for connected publishers versus manual application plus report_publication gives concrete when-to-use guidance.

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