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

Annotations only say idempotentHint=true and destructiveHint=false; the description adds the real behavioral context a caller needs: a group is created and a message is sent as the user, server-side checks cover introduce permission, participants, blocking, and rate limits (10 per manager per day across organizations), and an existing group returns conversationId without re-sending the opener. That last point is consistent with idempotentHint, not contradicted by it.

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?

The critical side effect is front-loaded in brackets before any procedural detail, and every clause carries information. The delivery is dense and semicolon-chained, which slightly hurts scanability, but there is no filler to cut.

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, it covers authentication (login), authorization requirements, the confirmation flow, rate limits, and the return value (conversationId). An agent has everything needed to call it correctly on the first attempt.

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%, but the description adds meaning the schema does not: message must be the already-written opener the user has seen, previewHash must be the latest preview's hash and will be rejected if participants or content changed, and proposalId must not be substituted with an org-match pairId. These are exactly the semantic traps a caller would otherwise fall into.

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 precise verb and effect: it creates a new group and sends a message under the caller's own identity, and it scopes that to PAIR proposals only. It also names the near-miss sibling concept (org-match pairId) and rules it out, so the tool is distinguishable from introduce_organization_match_pair and create_network_introduction without opening their schemas.

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 an explicit two-phase protocol: first preview=true to show both parties and the message text, then the same parameters plus previewHash with preview=false to execute. It also states the exclusion (PAIR proposals only) and where proposalId comes from, leaving nothing to inference.

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