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

Annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotency, so the safety profile is covered. The description adds genuinely useful behavior: side effects are possible, the run is captured in FULL (output and traces intact), and it returns a run reference resolved via get_workflow_run.

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-loads the core action and stays information-dense with no filler sentences. It is somewhat long with multiple em-dash asides, but each clause carries distinct meaning.

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 no elaboration, and annotations cover the safety profile. The description still supplies purpose, side-effect warning, capture detail, and the follow-up tool, leaving nothing an agent needs to call it correctly.

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 the baseline is 3. The description reinforces the version semantics ('omit version for the latest draft') but adds little on slug vs schedule_id beyond what the schema already states.

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 ('fire a schedule ONCE, immediately, WITHOUT publishing') and clearly delimits it from publish_schedule and from automatic firing. Naming preview_dynamic_endpoint as its parallel further anchors the concept against a known sibling.

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 a concrete use case ('test a draft before it goes live') and routes follow-up to get_workflow_run, plus the reproduce-a-sampled-firing scenario. It stops short of explicit when-not-to-use guidance relative to run_workflow or list_schedule_runs, so it is clear context rather than full routing.

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