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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description earns credit by disclosing the non-obvious consequence (alerts are silenced, so a dead job goes unnoticed) and the `until` state machine plus the pending-snitch failure mode. It doesn't mention the response payload, but with no output schema that is a small gap.

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-loads the write classification and the core effect, then folds semantics, precondition, and endpoint into the same tight block. Every clause carries information; nothing is padding.

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 two-parameter mutation with no output schema, the description supplies the safety consequence, the resume-state semantics, the blocking precondition, and the underlying endpoint. Nothing an agent needs to call this correctly 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 coverage is 100%, so baseline is 3. The description goes beyond by explaining what 'unpaused' actually means operationally (stays paused until deadmanssnitch_unpause_snitch is called) and confirming 'healthy' as the default resume point, detail the schema's enum-less string description leaves implicit.

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 (pause) and resource (snitch) and immediately qualifies the scope with 'WRITE' and 'SILENCES its alerts'. The alert-silencing framing is what separates it from sibling unpause_snitch and get_snitch without the agent needing to open any schema.

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 explicit when (silence a job's alerting), what happens if you don't (a stopped job goes unnoticed), the alternative route back (deadmanssnitch_unpause_snitch via 'unpaused'), and a concrete exclusion: a pending snitch that has never checked in cannot be paused. That covers use, alternative, and when-not in three clauses.

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