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

Annotations only declare the generic safety/behavioral hints (non-read-only, non-idempotent), so the description earns credit for disclosing the auth requirement (organization API key), the human-in-the-loop signing mechanism, and the returned approve_url — none of which appear in structured fields. It stops short of describing failure modes (e.g. expired requests, rejected signatures), which keeps it from a 5.

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 tight sentences: what it does, what it returns, and the workflow gate, all front-loaded. Nothing is redundant with the schema or annotations.

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 mutation tool with no output schema, the definition still supplies the return shape (approve_url), the authorization prerequisite, and the surrounding call sequence. An agent has everything needed to invoke it and act on the result.

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%, so every parameter (policy, stream_id, summary, details, hours) is already documented in the schema, including ranges and defaults. The description adds no syntax, format, or naming guidance beyond that, 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+resource ('Ask officers to authorize a sensitive action under a two-person policy') that an agent can distinguish from approval_request and fortress_tpi_execute. The return value (approve_url) and the policy scope are named explicitly, so the tool's role in the TPI flow is unambiguous.

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?

Gives an explicit gating condition ('Do not act until fortress_tpi_status shows authorized') and names the correct next tool (fortress_tpi_execute). It routes the agent across siblings both before and after this call, which is exactly what the usage dimension asks for.

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