gate_decision

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses key behaviors: PREVIEW does not act, COMMIT requires matching inputs, mints a tamper-evident receipt, returns an execution permit, and the tool is stateless. It also mentions optional attestation fields. This is substantial, though it omits error handling (e.g., what happens if inputs don't match) and any permission requirements, so a perfect score is not warranted.

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 three sentences with front-loaded key information ('Two-phase decision gate'). Each sentence adds unique value: the first defines the overall structure, the second details both phases, and the third covers statelessness and optional attestation. No redundant words or repetition of schema fields.

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?

Given the tool's complexity (8 parameters, output schema present, related sibling tools), the description covers the essential workflow well: it explains the phase sequence, the importance of preview_id, and optional attestation. The presence of an output schema means return values don't need detailing. Minor gaps include the lack of prerequisites or edge cases, but overall it is sufficiently complete for an agent to understand the tool's context.

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 8 parameters with 0% description coverage, so the description must compensate. It does clarify the meaning of 'phase' (PREVIEW/COMMIT), 'preview_id' (needed for COMMIT), and identifies three optional attestation parameters. However, it does not explain the required parameters 'action', 'resource', and 'context', which are central to the tool's purpose. This partial compensation earns a mid-range score.

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 is a 'two-phase decision gate' and describes what happens in each phase: PREVIEW returns a risk assessment and preview_id without acting; COMMIT requires preview_id, verifies inputs, mints a receipt, and returns an execution permit. This distinguishes it from sibling tools like mint_receipt and verify_receipt, which focus on receipts rather than the full decision workflow.

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?

Usage is implied through the phase description: an agent should use PREVIEW first to get a risk assessment, then COMMIT with the preview_id to finalize. However, there is no explicit statement about when to choose this tool over alternatives (e.g., check_egress or run_exit_drill), nor any exclusion criteria. The description lacks direct 'when to use / when not to use' guidance.

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