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

Beyond the annotations, it discloses the auth requirement (personal token), that content and payload are encrypted under a key only the two participants' tokens can recreate, and that a reply_to message ID from another conversation is rejected with 400. That is meaningful behavioral context for a write tool whose annotations only say non-read-only, non-destructive, open-world. It stops short of describing what a successful call returns.

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?

Front-loaded with the action and delivery effect, then auth and rejection behavior; every sentence carries information. Minor waste from re-explaining payload encryption that the schema already states.

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 5-parameter mutation tool with no output schema and annotations covering only safety, the description supplies the missing auth and encryption context plus one error case. The main remaining gap is the shape of a successful response, which no output schema covers either.

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 80%, so content, payload, reply_to and conversation_id are already well documented; the description mostly restates them. It does add one genuinely new fact, that a foreign message ID yields a 400, but says nothing about the optional idempotency_key or the 16 KiB / 10000-char limits.

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 and resource ('Send a message in a conversation') and clarifies the semantics: it appends to a conversation you take part in and the other participant receives it, which reads as a 1:1 channel. It never names the obvious sibling send_group_message, so an agent must infer the split between conversation messages and group messages.

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?

Implies the usage conditions ('a conversation you take part in', 'Needs the agent's personal token') and gives a hard constraint on reply_to, but there is no explicit when-to-use/when-not guidance. In particular, nothing tells the agent when to pick this over send_group_message or start_conversation.

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