send_messageSend a message in one of the user's active introductions (an accepted match). Use this only after the user has approved the exact text. Chat is free once an introduction is accepted; if a limit applies, the error explains it.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| match_id | Yes | ||
| join_code | No | The join_code from sign_up, when a new member saved their join answers in this conversation |
Changes observed during successful MCP inspections.
Input schema / properties / join_codeAdded value: +{
+ "description": "The join_code from sign_up, when a new member saved their join answers in this conversation",
+ "type": "string"
+}Input schema / properties / claim_codeRemoved value: -{
- "description": "The claim_code from sign_up or sign_in, if the account is not connected in this conversation",
- "type": "string"
-}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (non-read-only, non-idempotent, non-destructive, open-world). The description adds meaningful context beyond that: the user-approval gate before sending, that chat is free post-acceptance, and that limit errors are self-explaining. It doesn't warn about duplicate sends despite idempotentHint=false, which would have been valuable.
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?
Three short sentences, each earning its place: capability, precondition, and cost/error behavior, with the capability front-loaded. No redundancy or filler.
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 and only three simple parameters, the definition covers the essentials: what it does, the approval gate, and how quota errors surface. Minor gaps remain around duplicate-send behavior and the join_code path, but nothing blocks correct invocation.
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 only 33% (only join_code is documented), so the description must compensate. It partially does: 'accepted match' clarifies match_id's domain and 'the exact text' the user approved clarifies the text parameter's provenance. It adds no format or length guidance and says nothing about join_code, leaving real gaps.
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') and scopes it to 'one of the user's active introductions (an accepted match)', which implicitly separates it from send_intro_request and read_thread. It stops short of naming a sibling explicitly, so differentiation is inferential rather than stated.
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 a clear precondition: 'Use this only after the user has approved the exact text.' That is a real gating rule an agent can act on. It does not, however, contrast against alternatives (e.g., read_thread for reading, send_intro_request for starting a conversation) or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.