request_authorization

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

The description discloses key behavioral outcomes: auto-lock mints a receipt, HITL_REQUIRED waits for an approver, hard fails return a structured deny, and the result is recorded on the audit ledger. This gives a clear picture of side effects and failure modes, especially since no annotations are present.

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 relatively concise but uses specialized jargon ('auto-lock', 'HITL_REQUIRED', 'hard fails') that may be unclear without additional context. The structure is acceptable but could be more streamlined to avoid ambiguity.

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 does not explain how the signed receipt is used, what constitutes a 'scoped reference tool', or what the expected output format is. With no output schema and only partial parameter documentation, an agent would struggle to invoke this tool correctly in a real scenario.

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 schema has 7 parameters but only 3 have descriptions (tool, args, approver), and the description does not explain any of them. Parameters like scope, policy, ttl_seconds, and committed_today are entirely undocumented both in schema and description. The description adds no semantic value for parameters, failing to compensate for the 43% schema coverage.

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 action ('Request a signed authorization receipt') and the target ('scoped reference tool') with concrete examples like place_equity_order, wire_treasury_transfer, and rebalance_portfolio. It is specific enough for an agent to understand the tool's primary function, though it could be slightly more explicit about the 'signed receipt' concept.

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 mentions outcome branches (auto-lock, HITL_REQUIRED, hard fail) but does not explicitly state when to use this tool versus siblings like evaluate_spend_gate or approve_spend. No guidance is provided on when this tool is the appropriate choice, leaving the agent to infer context.

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