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

Annotations already indicate a write operation (readOnlyHint=false), and the description adds valuable behavioral details: auth mode restrictions, the response-gate mechanism, damping factors for cooldownSec and responseProbability, and the multi-agent turn-handoff pattern. These go beyond the annotations and schema, providing the agent with crucial behavioral context.

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?

Three sentences, front-loaded with the core action and endpoint, then key constraints, then multi-agent usage. Every sentence adds value with no fluff. The structure is logical and easy to scan.

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 19 parameters and no output schema, the description covers the essential context: what the agent is, auth modes, the multi-agent recipe, and pointers to a quickstart. It doesn't list every parameter (that's the schema's role) but provides the high-level understanding an agent needs to use 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?

The schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds extra meaning beyond the schema: it explains the multi-agent workflow, mentions the response-gate settings as a group, and clarifies auth mode limitations. It doesn't detail every parameter but adds meaningful usage context that isn't in the schema. This lifts it above baseline.

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 action 'Create a reusable AI agent' with the specific endpoint (POST /v2/apps/:appId/agents). It distinguishes from siblings like update, delete, clone, and invite-to-chat by explaining that this creates the persona, while others handle subsequent steps. The purpose is unambiguous and well-differentiated.

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?

Explicitly states when to use this tool (create agents) and how to use it in multi-agent scenarios: create each agent separately then invite them to a chat. It also specifies auth mode constraints (user/B2B accepted, app-token not accepted) and points to a quickstart recipe. This is clear guidance on when and how to invoke the tool.

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