martin_pause

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

Annotations set destructiveHint=true and idempotentHint=false. The description adds that the request is 'durable' but does not elaborate on what destructive effects or side effects occur (e.g., state changes, interruption consequences). It provides some context beyond annotations but not enough for full transparency.

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 a single sentence that front-loads the core purpose. Every word serves a function; there is no redundancy or filler.

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 6 parameters with zero schema descriptions, a oneOf constraint, and an existing output schema, the description is too brief. It lacks critical details like parameter explanations, the oneOf behavior, and output format, failing to provide sufficient context for correct invocation.

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?

With 0% schema description coverage, the description must compensate. It contains no information about any of the 6 parameters (file, loopId, latest, reason, runsDir, requestedBy) or the oneOf constraint, leaving the agent to infer solely from parameter names.

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's purpose: recording a durable pause request for a Martin run to indicate execution should pause before risky work. The verb 'record' and resource 'pause request' are specific, and the tool is easily distinguished from siblings like martin_cancel or martin_continue.

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 description implies usage for risky follow-up work ('execution should pause before risky follow-up work'), providing clear context. However, it does not explicitly state when not to use this tool or mention alternative sibling tools, lacking explicit exclusions.

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