chat_with_session

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

With no annotations, the description effectively communicates key behavior: the tool is non-blocking ('send and return immediately') and requires polling via poll_session for progress tracking. This adequately informs the agent of the tool's async nature, though it could detail error handling or response structure.

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 with two efficient sentences, front-loading the primary action and then directing to the tracking counterpart. Every sentence serves a purpose with no waste.

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 5 parameters, complete schema descriptions, and no output schema, the description covers the core usage pattern (send, poll). It lacks details about return format or error states, but the essential context for using the tool correctly is present.

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 100%, so the baseline is 3. The tool description adds no additional semantics beyond the schema descriptions, which already define each parameter. No improvement or degradation.

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 function: sending a task to a specified session and returning immediately. It uses a specific verb ('send'), clearly identifies the resource ('task' to 'session'), and distinguishes from sibling tools like poll_session by directing progress tracking there.

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 provides clear guidance: use this tool to initiate a task and then poll with poll_session for progress. It implies a fire-and-forget pattern, which helps the agent decide when to use this vs. other tools like watch_session or poll_session directly. However, it could be more explicit about when not to use it.

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