Build Human Approval Request

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

Annotations already establish readOnly, idempotent, non-destructive behavior, so the bar is lower; the description still adds real value by clarifying that no human is notified and nothing is stored, which resolves the apparent contradiction with the tool name. It also states the returned ID and expiry. It does not cover validation rules or error conditions.

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?

Two tight sentences, zero filler, with the create action and its critical no-side-effect caveat front-loaded before the return-value sentence. Every clause earns its place.

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?

With no output schema, the description correctly discloses the return values (request ID and expiry). All six parameters are described in the schema. It is largely complete, though it omits where the resulting ID is later consumed (e.g., add_approval_signature).

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 100% across all six parameters, so the schema already documents amount, reason, agent_id, currency, merchant, and expires_minutes. The description adds no parameter-level detail such as valid ranges for amount or units for expires_minutes, so it sits at the baseline.

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?

States a specific verb and resource ('Create an approval request record for a high-value purchase') and immediately qualifies the scope with 'without notifying a human or storing the request,' which is essential since the tool name implies a real notification. However, it never distinguishes itself from the sibling 'create_approval_request' with a similar name and intent.

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 phrase 'for a high-value purchase' implies the usage context, but there is no explicit when-to-use, when-not-to-use, or routing to alternatives such as create_approval_request or add_approval_signature. Usage must be inferred from the description.

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