session_message

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

Without annotations, the description carries the full burden for behavioral traits. It correctly implies mutation ('send') but is non-destructive. It adds the key behavioral detail about polling session_events to see the agent's response. No contradictions with annotations exist.

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 sentences long, front-loaded with the main action, and every clause adds value. It is efficient and well-structured with no wasted words.

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 tool's simplicity and the existence of an output schema, the description is largely complete. It covers the primary input, the expected follow-up action (polling events), and its role relative to siblings. Minor omissions like error conditions or rate limits do not significantly harm completeness.

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 input schema has 0% description coverage, so the description must compensate. However, it adds no meaning to the two parameters (session_id, text) beyond their names. It does not specify expected format, length, or examples, leaving the agent guessing about the text parameter's content.

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 user message to the agent — start work, reply, or continue a turn.' It specifies the verb (send) and the resource (user message to the agent), and distinguishes from siblings like session_start (new session) and session_respond (specific reply).

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 gives explicit usage guidance: 'Use to give the agent a new instruction or to resume an idle session.' It also advises the next step: 'After sending, OBSERVE by polling session_events.' While it does not explicitly list when not to use or alternatives, the context is clear enough for an agent.

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