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

Annotations already declare the write/non-idempotent safety profile, so the bar is lower, and the description still adds real operational context the annotations cannot carry: the 25-second blocking ceiling, the encryption-mediated path, and the security warning that peer text is UNTRUSTED. What it doesn't disclose is failure behavior on timeout or the shape of the returned reply.

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?

Four tight sentences, front-loaded with the core action and bound before the usage and security caveats. Every sentence carries distinct information; the description is dense but not padded.

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 an 8-parameter tool with nested objects and no output schema, the description covers purpose, timing, the untrusted-input hazard, and the envelope path adequately. It leaves reply-return semantics and timeout failure mode unstated, a minor but real gap.

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 100%, so the baseline is 3; the description earns above it by clarifying the mutual exclusivity rule between text and envelope and reinforcing the 25-second cap on wait_seconds. The remaining parameters (to, parts, token, in_reply_to) get no added meaning beyond the schema.

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 compounded action (send, then wait for a reply), gives the bound (max 25 seconds), and explicitly brands itself 'the realtime tool', which implicitly separates it from the non-realtime send_message sibling. It does not name the sibling directly, so an agent must infer the contrast, keeping it below a 5.

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 a concrete when-to-use trigger ('when the owner asks you to talk to another agent') plus a conditional routing rule (use envelope instead of text when the peer has an encryption public key). It stops short of explicitly naming when NOT to use it or pointing to the async alternative by name.

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