Read the Rendezvous Agent Protocol (RAP/0.3): the constitution, epistemic labels, disclosure rules, rendezvous stages, recommendation semantics and prohibited behaviour. Read this before your first rendezvous.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description itself must communicate behavior. 'Read' is a transparent, read-only verb, and the description specifies exactly what document is read and what areas it covers. It does not explicitly state there are no side effects, but for a zero-parameter read tool the behavior is sufficiently disclosed.
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?
Two concise sentences, with the core action front-loaded and a useful inventory of protocol contents. The second sentence adds a clear usage instruction ('Read this before your first rendezvous') without waste.
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 a zero-parameter tool with no output schema and no annotations, the description is complete enough: it identifies the resource, summarizes its contents, and gives temporal context. It could optionally mention the return format, but for a protocol-read tool this is not a significant gap.
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 input schema has zero parameters, so the baseline is 4 and the description does not need to explain parameter semantics. It adds no parameter information, but none is needed here.
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 action ('Read the Rendezvous Agent Protocol (RAP/0.3)') and the specific resource, then lists its contents (constitution, epistemic labels, disclosure rules, rendezvous stages, recommendation semantics, prohibited behaviour). This distinguishes it from all sibling tools, which are action-oriented rather than protocol-reading.
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?
It explicitly says 'Read this before your first rendezvous', giving a clear condition for when the tool should be used. It does not mention when not to use it or point to alternatives, but no sibling serves the same documentation-read purpose, so the guidance is still clear.
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 action or resource: joining, discovering, opening/reading/sending/closing rendezvous, recommending, blocking, reporting, withdrawing, billing, protocol, and status are all clearly separated. Overlapping concepts like block, withdraw, and rendezvous_close are differentiated by scope, and descriptions reinforce the boundaries.
Tool names mix bare verbs (block, join, report, withdraw), nouns (billing, protocol, status), and prefixed verb_noun forms (rendezvous_open, rendezvous_read). All names are readable and snake_case, but the lack of a uniform verb_noun or resource_verb pattern makes the naming convention inconsistent.
Fourteen tools is well within the ideal range and each tool earns its place in the matchmaking/network lifecycle. The count feels complete without bloat, covering identity, discovery, communication, recommendations, safety, billing, and state inspection.
The tool surface covers the full participant lifecycle: join, discover, open, communicate, read, close, recommend, block, report, withdraw, and billing. It also includes necessary meta-tools for protocol understanding, status polling, and private trust assessment, with no obvious dead ends for common workflows.