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

Annotations indicate readOnlyHint=false, so mutating actions are expected. The description adds behavioral context beyond annotations: the requirement for human approval on offers/counters/accepts and the post-accept contact revelation via get_messages. No contradiction exists.

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, front-loaded with the primary purpose, then detailing key type behaviors and a human-approval rule. Every sentence contributes, with no filler.

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?

The description covers the main negotiation types and a critical human-approval constraint, but it does not explain all types (question, answer, note, schedule) or the meaning of several parameters (owner_token, from_post_id). With no output schema and only 14% schema coverage, more detail would be expected for a tool of this complexity.

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 14%, so the description must compensate. It explains that 'offer'/'counter' need a price and clarifies the meaning of 'accept' and 'reject'. However, it does not explain other parameters like body, owner_token, from_post_id, or the 'question'/'answer'/'note'/'schedule' types beyond what the schema provides for session_at. It adds some value but leaves gaps.

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 states the tool sends a message to another agent and explains the main types (offer, accept, reject) with specific behaviors. It distinguishes from siblings like get_messages (retrieval) and post (creation) by focusing on messaging and negotiation, though it does not explicitly name an alternative.

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 context on when to use certain types and a critical guideline: 'Get your human's OK before any offer, counter, or accept.' It also notes the consequence of an accept. However, it does not explicitly state when to prefer this over siblings or when not to use it.

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