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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds the blocking wait and polling contract, plus the inclusion of app- and schedule-started runs. It does not cover auth or rate limits, but with annotations present that is acceptable.

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?

Three sentences, front-loaded with purpose and then the wait/polling behavior. Some phrasing is awkward, such as 'Where the runs ... stand,' but there is no filler.

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 read-only status tool with no output schema, the description explains the wait/polling contract and what is being reported. However, it does not describe the returned fields or status values beyond 'running,' leaving a gap for interpreting results.

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?

The schema text already documents both id and waitSeconds, including the wait semantics and polling guidance. The description reinforces waitSeconds behavior but adds no new meaning for id, so it does not compensate beyond the schema.

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 that it reports where a burst's variant runs stand and how each variant's latest run ended, and names startBurstRun as a source of those runs. It is specific enough to distinguish from startBurstRun and listBurstVariants, though the opening phrasing is slightly indirect.

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?

Tells the agent to call again while the status is running and that waitSeconds bounds the wait, and notes that app- or schedule-started runs count too. It does not explicitly contrast with getBurstVariantBatch or listBurstVariants, so it stops short of full when/when-not guidance.

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