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

Without annotations, the description carries full burden. It discloses key traits: the tool is asynchronous ('does not wait'), requires a company scope, has a sensitive approval tier, and mentions first-use manager approval flow. This provides rich context beyond what structured fields offer, though it could specify whether the activity runs immediately or is queued.

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 two compact paragraphs with no wasted words. The first paragraph states the core action and async behavior. The second paragraph adds approval context. It's well front-loaded, though the approval bracket could be more concisely integrated.

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 complexity (5 params, async, approval-sensitive) and no output schema, the description covers the input side well (async behavior, reason override, approval tiers). It does not describe what the returned response looks like, but the context does not require it for agent decision-making.

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% and description adds value by clarifying 'reason' overrides the activity's standing description, and 'resume_run_id' continues hung jobs. These details go beyond parameter names and schema descriptions. The agency of the tool is well contextualized.

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 it triggers a specific agent to run a specific activity, dispatches work immediately, and returns without waiting. It uses specific verbs ('trigger', 'direct') and resources ('agent', 'activity'), and the async behavior distinguishes it from synchronous execution 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 states when to use it ('to direct agents to take action') and mentions sensitive-tier approval flow, but does not explicitly contrast with sibling tools like 'add_agent_activity' or 'deactivate_agent'. No when-not-to-use guidance is given, missing a chance to clarify when other tools are better suited.

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