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

Goes well beyond the annotations: discloses the transactional, all-agents-at-once effect, that the pause is recorded server-side so any surface can resume, the refusal-on-already-paused behavior, the required permission, and what is unaffected (chat/diagnosis) and not done (no live-session cancellation). Note the 'not idempotent' behavior it describes matches idempotentHint=false, so no 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 action, then layered with behavior in a compact run of clauses. It is denser than most definitions but nearly every sentence carries decision-relevant information; only the CLI-twin parenthetical adds little for an agent.

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 single-optional-param mutation with no output schema, the description supplies everything needed: what changes, that it is all-or-nothing and reversible via resume, the failure condition, and the required permission. Nothing an agent needs to invoke it 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% and the single 'reason' parameter is already documented in the schema as 'shown with the pause record'. The description adds no syntax, format, or constraint beyond that, so the baseline of 3 applies.

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 autonomous AI actions for the organisation') and immediately scopes it: disables the auto-remediation policy and pauses every enabled agent. It explicitly distinguishes itself from the kill switch and from resume, so an agent can place it correctly among the ai.* 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 when-to-use context (pause all autonomy in one transaction), a when-not condition ('Refused when already paused'), and a prerequisite ('Requires ai.manage'), plus the scope boundary that chat and diagnosis keep working. It implies but never names resume_ai_autonomy as the counterpart, so the routing is slightly short of explicit.

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