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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and closed-world, so safety is largely covered structurally. The description still adds meaningful behavioral context: it explicitly reassures that no message leaves the system and imposes a 'public-safe' constraint on the content supplied. It does not describe how classification results are surfaced, but the output schema covers that.

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?

A single sentence with the core action front-loaded and the non-sending guarantee immediately after it; the sibling pointers are compactly parenthesized. No sentence is wasted.

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 two-parameter, non-destructive tool with rich annotations and an output schema, the description covers the action, the no-side-effect guarantee, and downstream alternatives. The only minor gap is that 'classify' is not elaborated, but the output schema is the appropriate place for that.

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%, with both parameters documented inline ('Public, non-sensitive collaboration need.' and 'Preferred public interoperability protocols.'), so the baseline is 3. The description's 'public-safe' framing echoes the request parameter's own description and adds no new syntax, format, or limit detail 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?

The description uses specific verbs ('Classify and prepare') on a concrete resource ('public-safe agent-to-agent collaboration need'), which tells an agent this is a dry-run/classification step rather than a dispatch. It names two sibling tools for follow-up, though it does not spell out the exact boundary condition that separates this tool from them.

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?

'nothing is sent' plus the parenthetical pointers to prepare_outbound_invitation and human_bridge_request give clear routing context for what to do instead when an actual send or human escalation is needed. It stops short of explicit when-to-use triggers (e.g., 'use before drafting an invitation'), so it is strong rather than complete.

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