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

The description discloses several important behaviors: cost/fallback logic (BYO key then managed wallet), possible NO-OP with specific skip reasons, error handling with actionable messages, and return value (run id). It also clarifies that it is not idempotent (fires a run). This adds substantial context beyond the annotations, which only set readOnly/idempotent/destructive hints to false.

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 yet information-dense. It leads with the primary action, then covers costs, NO-OP scenarios, error handling, return value, and access tier in a logical sequence. Every sentence adds value, and nothing is redundant or irrelevant.

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?

The tool has moderate complexity (costs, fallback, possible skips), but the description fully covers the essential behavioral aspects. It explains when it might not actually run and why, what the caller gets back, and the access restriction. Since an output schema exists, the description need not detail the response structure. This is complete for an agent to decide and invoke the tool 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?

With only one parameter (agent_id) and 100% schema coverage, the schema already gives the basic definition. The description adds valuable extra semantics: the agent must be one of the 'caller's own standing agents' and mentions the agent_type distinction (autonomous vs. workflow), which affects cost and behavior. This goes beyond the schema's simple 'Identifier of the agent to run now.'

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 a specific action: 'Fire one of the caller's own standing agents now, out of band from its schedule.' It distinguishes the tool from scheduled execution and from related tools like run_workflow, get_agent_run, and schedule_task by focusing on immediate, out-of-band execution of an existing agent.

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 gives clear context for when to use the tool (immediate execution vs. scheduled), explains cost implications for autonomous agents, and notes the tier restriction (sp500+). It does not explicitly name alternative tools or state when not to use it, but the distinction between agent types and the follow-up reference to get_agent_run provide useful guidance.

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