connect_agent_prompt

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the blocking nature ('up to 60s'), the session continuation pattern, and a warning about the requester field. However, it does not mention whether the call has side effects, what the response looks like, or any error conditions. For a tool that likely produces an agent reply, the absence of return semantics is a gap, but the disclosed blocking time and session rules add value, justifying a moderate score.

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?

Three sentences, all substantive. The primary purpose is front-loaded, followed by critical operational details (blocking, session handling, and a prohibition). Every sentence earns its place; there is zero fluff. This is a model of efficient description writing.

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 tool with only two parameters, no output schema, and no annotations, the description covers the key usage mechanics but omits return value description and error handling. Since it is an agent turn, the output is likely a natural-language reply, but that is not stated. The blocking time is a valuable detail. It feels adequate but incomplete; the agent would benefit from knowing what the tool returns or whether it can fail. This nudges the score to a 3.

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 0%, so the description must explain parameter meaning. The description does this effectively: 'prompt' is implied by 'natural-language agent turn' (the user's message), and 'sessionId' is explicitly explained with start/continue semantics. It even warns about a non-schema 'requester' field. This goes beyond the bare schema and compensates for the lack of schema descriptions, though it could more explicitly name the prompt parameter as the input text.

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: 'Natural-language agent turn for Farcaster/Lens cohort discovery.' This clearly conveys that the tool handles a conversational exchange for cohort discovery on those platforms. It distinguishes itself from siblings like connect_get_price or connect_lookup, which are query tools, by positioning itself as an agent-driven dialogue interface. The verb 'agent turn' is specific and unambiguous.

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 operational guidance: 'Omit sessionId to start; include to continue' and 'Do not send requester.' This tells the agent exactly how to structure calls across the session lifecycle. It provides clear context on when to use the tool (for natural-language cohort discovery) but does not explicitly mention when to use an alternative, though the sibling naming makes the division obvious. Lacking an explicit 'when-not' clause drops it from a 5 to a 4.

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