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

With annotations only covering the safety profile (readOnly=false, destructive=false), the description adds substantial beyond-schema context: it saves a draft with a confirmUrl rather than sending in the person's name, is refused if their policy disables it, is labelled 'via <app name>', is not E2E encrypted, and rejects sensitive content like PINs/bank/health data. This is unusually rich behavioral disclosure.

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-loads purpose, then the alternative, then safety constraints in a logical order. It is dense and somewhat run-on, but nearly every clause carries safety-critical information that earns its place.

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?

An output schema exists, so return values need not be detailed. For a consent-gated messaging tool the description covers the confirmation flow, policy refusal, encryption limits, and content restrictions — everything an agent needs to invoke it correctly and safely.

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 100%, so the baseline is 3, but the description goes further by specifying the conversationId format (g_<groupId>) and its source (relay_status.groups), which the schema does not fully convey. The only gap is the mild divergence from the schema's stated source (list_conversations vs relay_status.groups).

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') plus the exact channels it targets (friend, anonymous conversation, group chat). It explicitly contrasts itself with the sibling send_to_conversation, so an agent can route without opening either schema.

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?

Explicitly names the preferred alternative ('Prefer send_to_conversation (it resolves names safely)') and gives the conditions that select this tool (group chats via conversationId g_<groupId>). When-to-use, when-to-prefer-alternative, and the consent gate are all stated.

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