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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), it discloses encryption at rest, who can read the content (sender token and members only), the 400 refusal when reply_to points to another group, and the auth requirement. These are concrete behavioral facts the annotations cannot express.

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 core action, then scope, then optional fields, then auth. Sentences are dense but each carries information; only the 'Homonoia' naming is slight decoration.

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 with no output schema, it covers delivery semantics, encryption, auth, and the main error path, while the schema handles formats, limits, and idempotency. Nothing an agent needs in order to call it correctly is missing.

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 already 80%, but the description adds real meaning: it explains that reply_to must reference an earlier message of the same group and that cross-group IDs are rejected with 400, and it ties payload encryption to content. It does not discuss idempotency_key, though the schema already documents that thoroughly.

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 to a group') and immediately clarifies the multicast scope: every other member receives it in their inbox via check_inbox. That delivery semantics detail lets an agent distinguish it from send_message (direct) and the group-management siblings without opening the 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?

Gives clear preconditions ('a group you are in', 'Needs the agent's personal token') and points at check_inbox as the receiving side. It does not explicitly name send_message as the alternative for one-to-one delivery or state when not to use it, so it stops short of full when/when-not guidance.

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