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

Despite annotations only saying readOnly=false, openWorld=false, idempotent=false, destructive=false, the description discloses substantial behavioral nuance: autonomous runs cost money and settle against a BYO key first, workflow runs are free/deterministic, and the call can legitimately return a SKIPPED error for specific business reasons rather than silently succeeding. It also states what success returns and directs the caller to get_agent_run. This is exactly the kind of side-effect and failure-mode transparency annotations do not provide.

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 dense but every sentence earns its place: it front-loads the core action, then covers cost implications, the legitimate no-op failure mode, success behavior, and access tier. No filler or repetition of schema content; the structure flows logically from invocation to side effects to outcomes.

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 tool with one parameter and an output schema, the description is exceptionally complete. It covers what happens on success, what happens when a run is skipped, cost/funding behavior for both agent types, tier restrictions, and where to fetch status later. An agent has everything needed to invoke this correctly and set expectations for the response.

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?

The schema already fully documents agent_id as 'Identifier of the agent to run now,' so the baseline is 3. The description adds meaning beyond that by clarifying that the agent must be one of the caller's own standing agents and by linking agent_type to cost behavior, which helps the caller choose a valid ID. It does not add format details, but the schema's min/max length already handles that.

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 opens with a specific verb ('Fire'), identifies the exact resource ('one of the caller's own standing agents'), and scopes the action ('now, out of band from its schedule'). This clearly distinguishes the tool from scheduled agent execution and from sibling tools like schedule_task or run_workflow, so an agent can tell what it does without examining schemas.

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 clearly states when to use the tool: to trigger a standing agent immediately outside its schedule. It also gives important usage context around costs, free workflow agents, and legitimate no-op outcomes. It does not explicitly contrast itself with run_workflow or schedule_task, but the 'standing agents' and 'out of band' framing plus the reference to get_agent_run for follow-up provides practical routing guidance.

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