Courier: submit a signed CALL envelope (pk+sig+body) to the wire. Agent-native dealing — MCP is the sole surface. You sign locally, the wire routes.
| Name | Required | Description | Default |
|---|---|---|---|
| envelope | Yes | signed envelope { pk, sig, body }: body is canonical-JSON of {v,conv,n,ts,type:'CALL',from,body:{callee,instrument,sealed?,x25519_pk?}} |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It mentions 'sign locally' and 'wire routes', but does not state whether the operation is destructive, requires authentication, has side effects, or returns a confirmation. The mutation nature is implied but not explicit.
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 description is extremely concise, with two sentences that front-load the purpose and process. Every word contributes meaning, and there is no redundant or irrelevant content.
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?
Given the complexity of sending a call and the lack of an output schema, the description is incomplete. It does not explain the return value, error handling, prerequisites (like having a signed envelope), or whether the call is synchronous or fire-and-forget. The sibling tools might provide context, but the description itself is insufficient.
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?
The schema already covers 100% of parameters. The description adds significant value by detailing the envelope structure, especially the body's canonical JSON format with fields like 'callee', 'instrument', 'sealed?', and 'x25519_pk?', which go beyond the schema's minimal description.
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 clearly states the tool submits a signed CALL envelope to the wire, using specific terminology like 'Courier' and 'MCP is the sole surface'. However, it does not explicitly differentiate this tool from siblings like 'send_env' or 'post_axe', leaving some ambiguity.
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 description implies this is the primary tool for sending calls via MCP, but provides no explicit guidance on when to use it versus alternatives or when not to use it. The sibling list includes related tools, but no usage conditions are mentioned.
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.
Each tool targets a distinct aspect of the dealing wire (e.g., conv_status vs. deal_status, directory vs. instruments), with no obvious overlap. Descriptions clearly differentiate their purposes.
Tool names are mostly snake_case and descriptive, but vary between noun phrases (e.g., 'about', 'montage') and verb phrases (e.g., 'post_axe', 'send_call'). The pattern is not fully uniform but remains clear and readable.
With 18 tools, the server covers documentation, status queries, listing, and actions for a complex protocol. The count is well-scoped, avoiding both excess and insufficiency.
The tool surface provides full lifecycle coverage: reading schemas, posting axes, sending envelopes, polling rings, and inspecting deals and conversations. No obvious gaps for the stated purpose of agent-based dealing on the wire.