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

With no annotations, the description fully discloses behavioral traits: it's ALWAYS ASYNC and returns a chain_id immediately, the reply is not in the response, and a conversation can run for minutes. It also explains the difference between chain and job termination and identifies which polling endpoint is cheap vs heavy. This goes far beyond typical descriptions.

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?

Every sentence contributes critical information: purpose, async behavior, polling strategy, and multi-turn context. The description is longer than typical but each part earns its place and is logically structured in short paragraphs. No redundancy or filler.

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?

Despite having no output schema, the description explains the return (chain_id), how to obtain final results (poll ateam_chain_status, use ateam_get_chain once at end), and how to handle multi-turn. For a tool with async complexity and interaction with sibling tools, this is thoroughly complete.

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 covers all parameters so baseline is 3. The description adds meaning over the schema by explaining actor_id's role in multi-turn continuity, giving example message content, and clarifying that solution_id identifies the deployed solution. It doesn't repeat schema text verbatim, adding practical semantics.

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 tool's purpose: 'Send a chat message to a deployed solution.' It specifies the resource (deployed solution), the verb (send), and adds a key differentiator ('No skill_id needed — the system auto-routes'). This distinguishes it from sibling tools like ateam_chain_status and ateam_get_chain.

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?

Provides explicit usage guidance: never poll by job, poll by chain using ateam_chain_status, use ateam_get_chain only once at the end, and pass actor_id for multi-turn. It even names alternative tools and when to use them, which is excellent.

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