pause_runner

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

Goes well beyond annotations: it discloses the read-before-write sequence so prior state is recorded, the exact runtime effect (no new jobs picked up, in-flight jobs finish), reversibility, and a dry_run preview path. There is mild tension with destructiveHint=true, but pause is a reversible state change rather than data destruction, so this is a conservative-annotation mismatch rather than a contradiction.

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?

Front-loaded with the write/risk tag and then the single-sentence purpose; the Args block is warranted given 0% schema coverage. The dry_run preview instruction is stated twice (prose and Args), which is a small redundancy.

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 no-output-schema mutation tool, it covers the essential concerns an agent needs: safety class, reversibility, side effects on running jobs, and a preview option. It does not state permission requirements or what the read-before-write record enables on the return side, but nothing critical is missing.

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 carry the burden and largely does: runner is identified as an id sourced from list_runners, dry_run is explained as a preview toggle, and target is defined as a server name from config with 'omit for the default'. Only the runner id's format is left unspecified.

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 ('Pause a runner') and immediately qualifies it as reversible via undo, which cleanly separates it from resume_runner. A [WRITE][risk=medium] tag front-loads the operation class so an agent can place it among the read-heavy siblings.

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 clear context for when this operation is appropriate ('A paused runner stops picking up new jobs; running jobs finish') and points at undo as the inverse. It does not explicitly name resume_runner or undo_apply as the alternatives, so the routing guidance is implied rather than stated.

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