Send a message to an agent session

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

Annotations only give readOnlyHint=false / destructiveHint=false, but the description adds substantial context: calls return as soon as the prompt is queued (not when the agent replies), a grant to run the session's agent is required, and it enumerates 404 vs 403 semantics. It also documents visibility rules (UI-started sessions are creator-only and invisible to API keys; task-run/incident sessions are workspace-visible), which is exactly the kind of behavioral disclosure annotations cannot carry.

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 purpose, then async behavior, permissions, error codes, and visibility in a compact paragraph. Every sentence carries information; it is dense rather than bloated, though slightly long for a single-operation tool.

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?

No output schema exists, and the description compensates by explaining the return semantics (returns once queued, reply read elsewhere), permission requirements, failure modes (404/403), and visibility constraints. Nothing an agent needs to invoke it correctly appears to be missing.

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 only 50%, so the description should compensate, but it adds no meaning for the parameters. pipelineEditorContext is undocumented anywhere, and the description never explains the message payload or confirms session_id semantics beyond the ambient word 'session'.

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 a further prompt to an agent session.' The word 'further' distinguishes it from create_agent_session (which starts one) and the reply-reading sibling, so an agent can tell it apart without opening a 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 asynchronous interaction model and points to where the reply is read (GET /sessions/{session_id}/history/messages), which effectively routes to the history-messages sibling. It states the grant prerequisite. It does not name sibling tools directly or state when NOT to use it, so it falls short of 5.

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