Run the gate on a draft spec without releasing it. Review findings grouped by expected-output, interface, and prose classes, see what is approved, and read prose findings in full.
Run the gate on a draft without releasing it: findings grouped by class (expected-output / interface / prose), which are approved, and prose findings in full.
| Name | Required | Description | Default |
|---|---|---|---|
| draft_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden. It does disclose the output shape (findings grouped by class, approval status, full prose findings) and implies a non-mutating dry run, which is genuinely useful. However, it never explicitly states that no state changes occur, whether a review record is persisted, what errors look like for an invalid draft_id, or any permission requirements — gaps that matter for a gate tool with zero annotation coverage.
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?
A single front-loaded sentence with no filler, leading with the action and immediately qualifying it with the key constraint. It is dense with domain jargon ('the gate', finding classes), but nothing in it is wasted.
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?
An output schema exists, so the description need not explain return values, and the one-parameter surface keeps the tool simple. Still, 'the gate' is a domain concept left undefined, and the failure/error path for an invalid draft is unaddressed. Adequate minimum for a low-arity tool, but not thorough.
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 0%, so the description must compensate for the single draft_id parameter — and it does not. 'On a draft' only loosely gestures at draft_id without clarifying whether it is a spec ID, version, or handle, or whether an unknown ID triggers an error. The description adds essentially no meaning beyond the bare string field.
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 ('Run the gate on a draft') plus a scope qualifier ('without releasing it') that implicitly separates it from release_spec. An agent can tell this is a validation/dry-run tool, though the sibling that performs the actual release is never named, so differentiation is inferential rather than explicit.
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 'without releasing it' implies this is the pre-release check, which is real usage guidance against release_spec. But it never says when the gate must be run, what happens if the gate fails, or how this differs from other validation-adjacent siblings like check_rules, coverage, or audit_verify. Usage is left to be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.