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

Adds real context beyond annotations: the required write access (client or client owner) and the optimistic-concurrency requirement of the current revision. It also clarifies that no data is deleted, which usefully qualifies the destructiveHint=true annotation as 'stops work' rather than 'removes data' — a clarification rather than a contradiction. Does not state whether pausing is reversible without data loss beyond the retry note, or how quickly the stop takes effect.

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?

Two sentences, front-loaded with the effect, then permissions, then the non-destructive clarification and alternative. No filler and nothing buried.

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?

An output schema exists, so return values need not be described, and the definition covers effect, authorization, concurrency, and the reversal route. The remaining gap is the unexplained `accepted`/`fingerprint` inputs on a mutation tool, which an agent may have to infer from the pattern constraints alone.

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 60%; partnerId, installationId and expectedRevision are already documented in the schema, and the description only echoes the revision requirement ("the current revision"). The `accepted` and `fingerprint` parameters receive no explanation in either place, so the description neither compensates for the gap nor adds syntax or format meaning.

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 and resource plus the concrete effect: "Pauses an installation so its package setup and scheduled package work stop." An agent immediately knows what is halted, which distinguishes it from sibling apply/retry/offboard operations.

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 the reversal path explicitly ("use retry to queue it again") and clarifies the boundary "It does not delete anything," which tells the agent this is not a removal operation. Missing an explicit statement of when a caller should pause rather than offboard or revoke approval, but the context is clear enough to act on.

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