caravan_pay_revealUse a Phase-0 payment rail to reveal the matched test-network manifest. EXPERIMENTAL — TEST NETWORK ONLY — NOT A FINANCIAL PRODUCT OR SERVICE — NO REAL FUNDS — AS IS, NO WARRANTY, NO LIABILITY — USE AT YOUR OWN RISK
| Name | Required | Description | Default |
|---|---|---|---|
| poolId | No | ||
| payment | Yes | ||
| manifestId | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description includes important risk disclaimers about being experimental/test-network-only, but it does not explain actual side effects such as consuming payment, making an irreversible payment, or any destructive impact. The annotations already flag destructive/read-only traits, but the description adds no detail about what is destroyed or consumed.
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 compact and front-loaded with the core action, followed by concise risk disclaimers. There is no unnecessary elaboration or redundant wording.
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?
The description gives a high-level purpose and risk warning, but lacks essential context such as parameter semantics, what the output will be, and when to choose this over related sibling tools. The absence of an output schema and the detailed nested payment object make the description incomplete.
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 has 0% description coverage and the description does not explain any parameters. The poolId vs manifestId one-of relationship and the payment object with rail and paymentSignature are entirely unexplained.
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 a specific action ('reveal the matched test-network manifest') via a Phase-0 payment rail, and the title reinforces the 'pay to reveal' purpose. This distinguishes it from sibling tools like caravan_commit or caravan_get_match_status.
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 should be used when a match exists and a payment rail is needed to reveal the manifest, but it does not explicitly state when to use this tool over alternatives or provide exclusion criteria.
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 has a distinct purpose: posting intents/offers, committing, checking pools, polling match status, paying/revealing, attesting, and seller onboarding. No two tools overlap in functionality, and even similar-sounding ones (check_pools vs. get_match_status) target different objects (pools vs. intents).
All tools follow the same caravan_verb_noun pattern with snake_case, making the naming fully consistent and predictable. The prefix also clearly ties tools to the server.
With 9 tools, the set is well-scoped for a marketplace/aggregation service. It covers the core workflow without being sparse or overwhelming, fitting the recommended 3-15 range.
The tools cover the main lifecycle: posting intents and offers, committing, matching, payment, attestation, and seller onboarding. However, there is no explicit cancel/withdraw tool for intents or offers, which is a minor gap in full lifecycle management.