approve_spend

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

With no annotations, the description carries the full burden. It discloses a constraint (cannot approve BLOCKED) and a conditional side effect (mints a signed authorization receipt when tool and bound_args are supplied). This goes beyond a generic 'approve' statement, though it omits details like irreversibility or required permissions.

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?

The description is two tight sentences, front-loading the core purpose and then adding a key constraint and side effect. Every sentence earns its place, and it references spec sections for deeper detail without bloating the text.

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?

This is a complex tool with 8 parameters, nested objects, and no output schema. The description does not explain the structure or intent of the action and policy objects, nor what happens when tool and bound_args are absent, nor the return value. The agent would struggle to construct valid calls without additional knowledge from spec sections or examples.

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 only 50%, so the description should compensate for undocumented parameters like scope, action, policy, and committed_today. It only references tool and bound_args when explaining the receipt minting, adding no meaning to the other four parameters. This leaves the agent without guidance on how to populate critical nested objects.

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 clearly states the tool's function: human-in-the-loop approval for proposals that returned HITL_REQUIRED. It specifies the verb 'approve' and the resource (proposal), and distinguishes itself by noting it cannot approve BLOCKED/hard-rule failures. This sets it apart from sibling tools like request_authorization or issue_approval_receipt.

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 provides explicit conditions: use for HITL_REQUIRED proposals and avoid for BLOCKED/hard-rule failures. It does not name alternative tools for other scenarios, but the context is clear enough for an agent to know when to invoke this tool versus others.

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