clearances_create

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

With no annotations, the description carries the burden well: it discloses the async human-in-the-loop model, that a human must open approval_url to approve or deny, and the two ways to observe the decision. It omits auth/permission needs, idempotency, and whether the call blocks until decision.

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 short sentences, front-loaded with the action, then requirements, then the return value and the follow-up flow. No filler sentences; every clause conveys actionable information.

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?

No output schema exists, and the description compensates by naming the returned clearance and its key field (approval_url). The async decision flow is covered, but expiry behavior, error cases, and authorization requirements are left to the schema or unstated.

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 all eight parameters are already documented in the schema. The description only restates that title and scope are required and that callback_url is a decision-notification hook, adding little beyond the structured data. Baseline 3 applies.

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?

Specific verb+resource: "Create a human approval request" tells the agent exactly what it makes, and the returned approval_url makes the outcome concrete. It is clearly distinguishable from the approve/deny/revoke/list/get siblings, which operate on an already-existing clearance.

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?

States the required inputs up front and gives explicit next-step routing: poll clearances_get or pass callback_url to learn the decision. It does not say when creating a clearance is inappropriate versus e.g. verify_token, so it falls just short of full when/when-not/alternatives coverage.

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