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

Annotations are present but thin (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), so the description does real work: it discloses that pausing stops only future collection, that resuming/autopilot can start future outreach, that autopilot bypasses review, and that the call never sends messages. What it omits is the reverse side of those traits – that this is a mutation whose side effects may be hard to undo, and nothing about failure modes beyond the revision conflict. Useful, but not full behavioral coverage for a write tool.

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 and gated usage, then prerequisites, then consequences, then return value – a sensible order with no filler sentences. The autopilot parenthetical is dense but each clause (no review, daily budget pacing, batch-review Plays exempt) carries operational meaning. Slightly overloaded for a single tool description.

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 5-parameter mutation with a full schema and an output schema, the description supplies the prerequisite, the sibling alternative, the downstream effects of each flag, and the return value. It stops short of anything about permissions or the teammate-workspace implications, but an agent could call this correctly from what is here.

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 100%, so baseline is 3. The description adds genuine meaning for two parameters: expectedRevision as concurrency protection ('a stale revision is refused so a concurrent change is never overwritten') and autopilot as straight-to-sequence enrollment paced by the daily X budget. It says nothing about workspaceId or the omit-to-keep-current behavior of status/autopilot, which the schema already carries.

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?

Opens with a specific set of verbs and resource: pause/resume an X Play or toggle its automatic enrollment. It is immediately distinguishable from sibling set_sequence_status, which the description itself names as the tool for stopping queued sequence messages.

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?

Explicit gating ('only when the customer asks'), an explicit prerequisite workflow ('Read the Play with list_x_plays first and pass its revision as expectedRevision'), and an explicit alternative with its condition ('use set_sequence_status to stop those too when requested'). Also notes the batch-review class of Plays where automatic enrollment must stay off.

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