chat

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

With no annotations, the description carries the full load and does well: it discloses the failure contract ('returned as a tool error with a plain explanation'), the asynchronous mode and its immediate return value, and the per-session concurrency limit. It stops short of stating latency expectations for the default path or whether the call has side effects or cost, which are the remaining behavioral unknowns for a tool with zero annotation coverage.

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?

Front-loaded with the action and result, then ordered by operational concern (failure, session reuse, async mode, concurrency limit). Every sentence is useful, though the enumerated return fields (response, session_id, model, agent_logs) partly restate the output schema that already exists.

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 3-parameter tool with an output schema and no annotations, the description covers the call mechanics that matter: sync vs async, session reuse, error behavior, and concurrency. It is slightly thin on what happens to the default (wait=true) call if it runs long, and on any timeout or retry expectations.

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 description coverage is 0%, so the description must compensate, and it does for the two non-obvious parameters: wait is tied to the minutes-long async pattern, and session_id is tied to conversation continuation. user_input is left entirely to its name, so input formatting or length expectations are not stated.

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?

States a specific verb and resource ('Send one message to the AI Brainstem') plus the shape of what comes back ('return its answer as JSON'). It also implicitly separates itself from the sibling job_status, which it names only for polling, so an agent can tell which tool initiates work versus which retrieves it.

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?

Gives explicit conditional routing: wait=false is for 'work that may take minutes' and requires polling job_status(session_id), while the default path returns the answer directly. It also names the continuation mechanism ('Pass the returned session_id to continue the conversation') and a hard constraint ('One message at a time per session'), leaving little to inference.

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