gate

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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower, yet the description still adds real value: it explicitly states the command is NOT executed and that the result includes a state plus an argv form. The closing line 'the exit code is the verdict' hints at how the result is consumed but is ambiguous for a tool that does not run anything.

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 sentences with the core behavior front-loaded and no filler. The compression comes at some cost to readability – 'as argv, with its state' is dense and the exit-code clause sits oddly in a description of a non-executing tool.

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 must carry the return contract, and it only gestures at it ('as argv, with its state'), leaving the structure of 'state' and the meaning of the exit-code verdict unclear. For a read-only lookup tool the gaps are survivable, but an agent would still not know exactly what it receives back.

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 coverage is 100%, so the schema already documents all three parameters, including the important 'omit gate for every gate the change needs' behavior. The description only implicitly touches on the gate and path parameters ('a named gate ... for a file') and adds nothing about the change class default.

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 says it returns 'the one command a named gate runs for a file, as argv, with its state' – a specific resource and output shape, though the verb is implicit (it's a lookup, not an action). It never distinguishes itself from the many sibling tools (headron, port, route, proof), and a reader must infer that 'gate' is a config-defined check rather than anything else.

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?

'It shows the command and does not run it' implies a dry-run/inspection use case, which is the closest thing to guidance here. There is no explicit when-to-use, no when-not-to-use, and no named alternative; the routing information about omitting the gate parameter lives only in the schema, not the description.

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