onboarding_post_wo_execute_plan

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

Annotations already declare readOnly=false, idempotent=false, openWorld=true, so safety baseline is given. But the description hides the most important behavioral trait: the body's subStage/retryCount/executionId/nextPageLink fields imply a resumable, step-at-a-time execution state machine, and nothing says execution is long-running, resumable, or that callers must drive it through stages. This is exactly the kind of context the description should carry beyond annotations.

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?

The core sentence is repeated twice verbatim with a trivial variation, then a raw POST path is appended. No wasted-length penalty for the useful clause, but the duplication shows no editing and the useful content is not front-loaded with any state-machine context.

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 non-idempotent, open-world mutation with a 14-property nested body, no output schema, and staged execution semantics, the description is far too thin. An agent cannot tell whether one call completes execution or whether it must loop through subStages, which is critical to calling 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 nominally 100% at the top level, so the schema is expected to carry parameter meaning and baseline 3 applies. In practice only planLink is documented and the nested body's 14 state-machine fields are opaque, but the description adds nothing either way, so it neither compensates nor misleads.

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 and resource ("Execute the given onboarding plan") and scopes it to the current organization, so an agent can tell it is a mutation of an existing plan. However, it does not distinguish itself from closely named siblings such as onboarding_get_wo_execute_plan, onboarding_get_wo_execute_plan_by_id, or onboarding_post_plan, leaving the agent to infer which one actually runs the plan.

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?

There is no guidance on when to use this instead of onboarding_get_wo_execute_plan(-by-id) or the plan/deployment endpoints, nor on prerequisites (does the plan need validating first?). The only usage clue is "current organization," which is a constraint, not a selection rule.

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