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

Adds real behavior beyond the annotations: single-use consumption, refusal when unauthorized, and an organization API key requirement. Annotations only say readOnly=false and idempotent=false; the single-use and auth semantics are the valuable additions. It does not say what happens to the action's result or failure modes beyond refusal.

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 clauses, zero filler, and the core semantics (consume, single use, auth requirement) are front-loaded. Nothing could be removed without losing meaning.

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?

For a non-idempotent mutating tool with no output schema, the description covers the key operational facts an agent needs: it consumes a one-time right, requires authorization and an org API key, and will be refused otherwise. It leaves the identity of the underlying action and the post-consumption outcome 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 description coverage is 100% and the single parameter (request_id, 'tpi_... ID') is already documented in the schema. The description adds no syntax, format, or sourcing hint for the ID, so the 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?

States a specific verb ('consume') and resource ('two-person authorization right') and clarifies the tool executes a previously-authorized action rather than creating or inspecting one. It does not explicitly name the sibling it must follow (fortress_tpi_request / approval_request), so it stops short of full differentiation.

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?

'Right before performing the action' and 'refused unless authorized' imply the precondition (an authorization must already exist), which is useful sequencing guidance. However, no alternative sibling is named and no explicit when-not-to-use is given, so the agent must infer the workflow from the family of tpi_* tools.

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