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

With no annotations, the description carries the behavioral burden, and it does disclose concrete behavior: the run is metered, goes through evidence/credit checks, and refuses with agent_evidence_unavailable before spending credits when no readable evidence exists. It stops short of describing success-side effects such as persistence, async completion, or what a returned run object contains.

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?

Two sentences, no filler: the first states the action and constraints, and the second states the key failure mode. The important refusal/cost behavior is front-loaded after the core trigger.

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 simple 4-parameter, no-output-schema tool, the description supplies the essential guardrail and cost behavior an agent needs before invoking. It does not mention how to obtain/verify the resulting run, but sibling tools like get_agent_run and list_agent_runs fill that gap implicitly.

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 100%, so the schema already documents agentKey, requestIdempotencyKey, modelId, and instructions. The description adds context about evidence availability but does not deepen the meaning of any individual parameter, fitting 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?

The description uses a precise verb-resource pair—'Trigger a metered manual managed-agent run'—and frames it as the dispatch action, which separates it from the many get/list siblings. The refusal condition adds a specific behavioral signature rather than a generic 'run an agent' phrase.

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?

It is clearly about initiating a run, so an agent can infer when to call it, but it never explicitly says when to prefer it over related tools like get_agent_run or list_agent_runs, nor does it state when not to use it. Usage is implied rather than stated as a rule.

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