Run a job's plan

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

Annotations already declare it a non-read-only, non-destructive, open-world operation. The description adds context annotations can't: it is an approval action a headless caller must supply, requires the write scope, and produces drafts rather than live deliverables. Only the failure/edge behavior (e.g., no pending plan) is unstated.

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 the action and followed by the trigger and prerequisite. The 'approval click a headless caller has nobody to make' phrasing is evocative but still carries information about the intended caller.

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 an output schema present, return values need no explanation, and the description covers action, trigger, auth scope, and the draft nature of outputs. Missing only edge-case behavior such as what happens when no plan is pending.

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 id and budgetUsd are already documented in the schema; baseline 3 applies. The description neither adds format guidance for the id nor explains the budget parameter's effect on the run.

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+resource pair: approving/running the job's newest proposed plan, which is clearly distinct from siblings like jobs_continue (resume work) or posts_approve (approve a post). The 'newest proposed plan' narrowing tells the agent exactly which artifact is acted on.

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?

"Use it after a turn ended with a plan waiting" gives an explicit triggering condition, so the agent knows when to fire it. It does not name an alternative tool or state a when-not case, which keeps it short of a 5.

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