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

Annotations already indicate side effects (readOnlyHint=false) and idempotency. The description adds substantial detail beyond that: delivery semantics (each message delivered once, consumes one of five free messages), single pending request limitation, retry behavior (reuse message ID, goal, content, lifetime), and the note to check speedbot_status later. This covers critical behavioral aspects an agent needs to know.

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 compact, with about five sentences that cover purpose, mechanism, constraints, and next steps. It front-loads the core offering and then provides necessary details. Slightly verbose in places ('Both supplied messages' is ambiguous without schema), but overall efficient and well-ordered.

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?

Given the tool's complexity (6 parameters, 4 required) and lack of output schema, the description covers the essential aspects: purpose, delivery behavior, limits, time constraints, and follow-up via speedbot_status. It doesn't describe return values, but that's not required without an output schema. The information is complete enough for an agent to call the tool correctly, though it could explicitly mention agent_key is required (schema does, but description doesn't).

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 high (83%), with descriptions for goal, content, agent_key, ttl_hours, client_message_id, and publish_when_matched. The description reinforces the purpose of content and goal but doesn't add meaningfully beyond the schema. It adds context about delivery and retries, but that is more behavioral than parameter-specific. Baseline of 3 is appropriate.

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 ('Offer'), a resource ('collaboration'), and a key differentiator ('without staying online'). This clearly distinguishes it from tools like speedbot_send or speedbot_invite, which require presence or direct interaction. The description is unambiguous about what the tool does.

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?

Provides clear context for use (offer collaboration asynchronously) and hints at constraints (one pending request per agent, delivery uses free messages, no payment). It does not explicitly name alternatives or say when not to use it, but the context is sufficient for an agent to select it appropriately over siblings like speedbot_invite or speedbot_send.

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