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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes further, revealing the synchronous vs. queued behavior, the return of a ticket_id, and the need to poll via actionlayer_get_action_ticket until is_terminal=true. It also clarifies that while pending there is no sub-status, which prevents misleading polling logic. This adds substantial behavioral context beyond the 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 description is concise despite its technical depth. Each sentence delivers essential information: the action invocation, the input constraints, the distinction from start_task, and the polling behavior. It is front-loaded with the core purpose and avoids filler. The structure with paragraphs aids readability without redundancy.

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?

Given the tool's complexity, the description covers all necessary calling details: how to form inputs, when to use the sibling, and how to handle both synchronous and async outcomes. Even though an output schema exists, the description precisely explains the `outcome='queued'` and `ticket_id` fields, removing ambiguity. Nothing essential for correct invocation is missing.

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 coverage is 0%, so the description must compensate. It thoroughly explains the `inputs` parameter, including the exact-match requirement and the exclusion of orchestration metadata, which is crucial. However, it does not mention the `executor` parameter at all, leaving it to the schema to convey its meaning and default. This partial coverage earns a 4 rather than a 5.

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?

The description clearly states the tool's core function: 'Invoke a single action with typed inputs.' This is a specific verb and resource, and it immediately differentiates from siblings by specifying that orchestration metadata belongs to actionlayer_start_task, not here. It also references actionlayer_get_action_ticket for polling, establishing a distinct role among the sibling tools.

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?

The description explicitly tells when NOT to use this tool: if you need idempotency_key, max_budget_usd, webhook_url, or deadline, call actionlayer_start_task instead. It also explains that API actions run synchronously while others return queued, guiding the caller on how to handle each case. This is clear, actionable usage guidance.

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