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

Beyond the annotations, the description discloses that the run consumes the automation's allowance like any scheduled run, that it will be refused when the monthly cap or run limits leave no room, and that the outcome is observable via read_automation. That is real operational context. It does not explain what makes the call destructive despite destructiveHint=true, nor does it mention the request_key idempotency contract the annotations imply.

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 short sentences, zero filler, and the core behavior (start now, bypassing the schedule) is front-loaded ahead of the cost and refusal details. Nothing repeats the annotations or the schema.

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?

Return values are covered by the output schema and the description still helpfully points at read_automation. But for a six-parameter tool with a nested arguments object, a catalog-version requirement, and a skills-proof array, the description leaves the entire invocation contract to the schema, which is only half documented.

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 only 50%, so the description should carry more of the burden, and it carries none: it never mentions work_id, the nested arguments.automation_id, read_skills, request_key, expected_catalog_version, or publication_proposal_id. The schema's own descriptions for automation_id, read_skills, publication_proposal_id, and expected_catalog_version are detailed, which partly compensates, leaving the baseline of 3.

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?

"Start one run now, outside its schedule" gives a specific verb (start) and resource (an automation run) plus the distinguishing property that it bypasses scheduling. It is clearly separable from schedule-management siblings such as activate_recurring_schedule, though it never names a specific sibling alternative.

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?

"Outside its schedule" implies the use case — an ad hoc immediate run — and the description states the refusal condition (monthly cap or run limits exhausted). However, it gives no explicit when-not guidance and does not point to alternatives such as native.recipe_run, native.run_workflow, or the scheduled-run paths.

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