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

Annotations already declare read-only/idempotent/non-destructive, and the description stays consistent while adding far more: asynchronous job with jobId, expected polling cadence, the failure modes of the alternative tool, the semantic weight of `incomplete` (not a pass) and `stale` (timeline edited mid-run), and the explicit coverage limitation that sound is not checked. This is exactly the context annotations cannot carry.

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 differentiating behavior, then the async workflow, then the result contract. Dense but nearly every clause is load-bearing; the inline enumeration of result fields is long but justified by the absence of an output schema. Minor cost: long compound sentences require careful reading.

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?

With no output schema, the description fully compensates by specifying the result object's fields, the meaning of each verdict value, the stale caveat, and the polling protocol. Preconditions and error code are included, so an agent has everything needed to invoke and interpret the call.

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 token, projectId, timelineId and cancel are already documented; the description adds only that nested timelines are verified too, which the schema already states for timelineId. It says nothing about when to use `cancel` beyond what the schema implies, so baseline 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 precise verb+resource ('renders a timeline the way an export does and reports what fails') and immediately contrasts with the sibling inspect_timeline, explaining the mechanical difference (preview path substitutes nearby pictures vs exact render). An agent can distinguish the two without opening either 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?

Explicitly names the alternative (inspect_timeline) and why it is insufficient, then gives operational guidance: poll get_job_status every ~5 s, re-verify when stale is true, and the precondition that the project must be open in the paired editor tab with PROJECT_NOT_OPEN otherwise. Both when-to-use and when-not-to-use are covered.

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