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

Annotations only declare readOnly=false, idempotent=true, openWorld=true and destructive=false; the description adds the operationally critical layer they omit: 0.10 USDC per call via x402 on Base mainnet with 10 free signed-wallet calls per rolling 30 days, X-Wever-Wallet-Proof binding exact JSON args and path, the X-Wever-Connect-Token credential, and the human-gated rule that contact details never enter a mailbox until both humans approve in plain language. That is exactly the beyond-annotation context an agent needs before spending money.

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 return value, then endpoint, then payment/auth, which is the right order for a paid mutation. It is dense with payment and header boilerplate, and the closing 'Stakes use the existing /first-dates/ flow' is tangential and adds ambiguity rather than value.

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?

With no output schema, the description correctly discloses the return (private human review link plus approval status), and it covers cost, auth headers, human approval gating and a recovery doc pointer — enough for an agent to invoke it safely. The remaining gap is parameter-level semantics (especially request_id) and any error/failure behavior.

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 0% for three required parameters, so the description carries the full burden and does not meet it. It implies two profile identifiers ('between two... profiles') but never distinguishes profile_id from other_profile_id, and never explains what request_id is for (presumably idempotency/retry dedup) or how it relates to idempotentHint. Only the regex patterns in the schema hint at format.

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 ('Propose one introduction between two human-approved opt-in profiles') with scope ('one') and preconditions ('meet each human's stated criteria'). This clearly separates it from sibling wever_matchmaking-opt-in-profile (prerequisite) and wever_matchmaking-approve-or-decline-intro (the counterparty decision step).

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?

The context for calling is clear: both profiles must already be human-approved opt-ins whose stated criteria match, and the description says matching uses only stated criteria. It points to /api/matchmaking-contract for setup/delivery/recovery. It does not explicitly name the opt-in or approve-or-decline siblings or state when not to use it, so it falls short of full routing guidance.

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