Send a follow-up message to a session

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

The openWorldHint annotation already signals that the tool may interact with external systems. The description adds useful context by stating that the agent retains previous context and can build on earlier exploration and edits, but it does not describe side effects on the session, response format, or failure behavior. This is adequate but not richly transparent.

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 with no filler. The first sentence states the core purpose, and the second sentence adds valuable context about state retention. Every word contributes to an agent's ability to decide whether and how to use the 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?

For a simple two-parameter tool with openWorldHint and no output schema, the description provides sufficient context: it explains the stateful nature, when to use it, and what the message is for. It does not explain return values or error handling, but these are less critical given the tool's simplicity and the explicit session_id and message schema.

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 both session_id and message are already documented. The description's mention of 'follow-up' reinforces that message is an instruction building on prior context, but it adds no new meaning beyond the schema. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 states a specific action ('Continue an existing delegated session with another message') that clearly distinguishes it from sibling tools like create_session, delegate_task, get_session, and abort_session. The emphasis on 'existing' and 'follow-up' makes it unambiguous that this is not for initiating or inspecting sessions.

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 clearly indicates when to use this tool: when a delegated session already exists and the agent wants to continue it. It does not explicitly name alternatives or state when not to use it, but the context provided (existing session, previous context) is enough to infer that this is the follow-up tool rather than a session creation or retrieval tool.

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