authorize_tool_call

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

With no annotations supplied, the description carries the transparency burden and does enumerate important denial cases: changed arguments, expiry/replay, MAC failure, host-bound override, and binding mismatch. It does not describe success return values or error channels, but the security-relevant behavior is well exposed.

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 sentences convey the operation, preconditions, and key failure modes without filler. Every sentence adds information needed to call or avoid misuse.

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 tool has nested call/policy/receipt objects and no output schema, and the description focuses on deny conditions rather than success output or parameter construction. It leaves some gaps around how to build policy and how signing_key is used, though the core authorization check is clear.

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 prose adds meaning for receipt, arguments, and host_bound by explaining which conditions cause denial. It does not clarify policy construction or the role of signing_key, and with only 50% schema coverage the description only partially compensates.

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 opens with a clear verb and object: authorize a tool call against a previously issued receipt. It immediately separates this from issuing or evaluating receipts and highlights the core precondition.

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 the required precondition (previously issued receipt) and warns that allowlist matches alone are denied, which tells callers when not to use it. It does not explicitly name sibling flows such as request_authorization or issue_approval_receipt, so it stops short of full alternative routing.

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