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

Annotations already declare destructive/openWorld/non-idempotent, and the description adds substantial context beyond them: approve publishes the business, reject requires a note the owner sees, approval is refused if the name changed, and recall removes the business from the catalogue and re-queues it. The name-race refusal condition is exactly the kind of hidden behavior an agent needs.

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?

It is dense but well front-loaded with the team restriction, then proceeds from the common case to the rename route and finally recall. Some sentences are long and pack multiple conditions, but each earns its place by covering a real branch.

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 destructive mutation tool with no output schema and only 25% schema coverage, the description covers the decision branches, the name-verification prerequisite, and recall's side effects. It does not describe what the caller receives on success, but with no output schema that is a minor gap.

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 only 25%, so the description must carry meaning and largely does: it explains note (owner-visible), expected_name (exact name previously shown, required except for rename route), and enumerates what approve/reject/recall do for decision. Only application_id is left undiscussed, and it is self-evident from the name and required-parameter status.

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 specific verbs (approve, reject, recall) acting on a specific resource (a business application), and names the sibling tool op_applications as the source of the application list. An agent can distinguish this from op_applications, op_decide_lead, and op_suspend_business immediately.

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 gives explicit when-rules: only for the Awning team, expected_name is required unless the route is rename, recall applies only to an approved application with route auto_branch, and it spells out the re-list-and-recheck workflow when approval is refused. Restrictions and alternatives are stated, not implied.

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