Message a Claude Code session

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write. The description adds genuine behavioral context beyond that: live windows receive within seconds, headless sessions answer on their next turn, and the call can be made synchronous via wait_seconds. It does not cover failure behavior for an invalid or ended session_id, which is the remaining gap.

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?

Four short sentences, purpose front-loaded, followed by the mode-specific delivery semantics and the wait_seconds opt-in. No filler or repetition.

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?

With no output schema, the description implies what comes back when wait_seconds is set ('the answer in this call'), covering the return behavior adequately. Missing only error/edge handling for unknown or terminated sessions, which for a 3-parameter tool is a minor gap.

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 coverage is 67%, with text and session_id already documented (including where the id comes from). The description compensates for the undocumented wait_seconds by explaining its purpose — blocking to receive the answer — which the schema only bounds numerically (0-45).

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 (send) and resource (a message to a Claude Code session) and names the two target modes, live and headless. An agent can distinguish this from read_messages or send_job without opening the schema.

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?

Explains the two operating modes and when wait_seconds is appropriate ('to get the answer in this call'), giving clear context for invocation. It stops short of naming alternatives such as send_job or stating exclusions, so no explicit when-not guidance.

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