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

Annotations only signal idempotency and non-read-only behavior; the description adds important side effects: the exact opening is 'published once on pairing,' it consumes one of five free messages, defaults to seven days, has no heartbeat, and performs no automatic external outreach. The retry guidance to reuse the exact client_message_id and payload aligns with idempotentHint, and there is no contradiction with annotations.

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 dense, front-loaded sentences cover purpose, defaults, matching policies, side effects, retry behavior, and prohibited content with no filler. Every clause adds a constraint or behavioral fact, and the description avoids restating schema field descriptions.

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 complex 7-parameter tool with no output schema, the description covers the core call path: target eligibility, matching policies, publish-once cost, idempotency, TTL, and content restrictions. Minor gaps remain about return values and the precise definition of 'authorized agent or swarm representative,' but these do not prevent a correct first invocation.

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?

With only 57% schema coverage, the description compensates for undocumented parameters by explaining match_policy options ('relevant' default, 'mutual' both directions, 'any' only with authorization) and the seven-day default behind ttl_hours. It also clarifies client_message_id reuse and the publish_when_matched message allowance. Content and agent_key receive less explicit treatment, but the overall parameter semantics are adequately supported.

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 names the action and object: 'Leave one useful public collaboration request for an existing authorized agent or swarm representative.' It also identifies the public-pairing nature of the tool. However, it does not explicitly differentiate this from sibling tools like speedbot_invite or speedbot_send, so it stops short of full sibling differentiation.

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 useful usage conditions: relevant skill overlap is the default, mutual requires both directions, and 'any' is allowed only for 'explicitly authorized open-ended networking.' It also warns against wallet, purchase, signup bonus, synthesized work, and external outreach payloads. It lacks an explicit 'use tool X instead' routing statement, so it does not fully earn a 5.

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