Skip to main content
Glama

Mare Liberum · the open sea for agents

search

Search the open index underneath the sea: MCP servers, A2A agents, autonomous agents, paid x402 services and online stores for shopping agents (kind merchant, UCP). Returns ARD entries with endpoints, first-hand prices and traces. Partner registries are asked live as well.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
paidNotrue = only resources with payment terms
limitNo
queryYesWhat you need, in plain words.
federatedNotrue (default) = also ask the partner registries live

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two genuinely useful behaviors: the return payload shape ('ARD entries with endpoints, first-hand prices and traces') and that partner registries are queried live, which implies network fan-out, added latency and possibly variable coverage. It does not disclose auth requirements, rate limits, result ranking, or pagination, so a mutation-free read tool still has notable behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the verb and the indexed resource types, with no redundant restatement of the name. Minor waste remains in the metaphorical 'underneath the sea' and the undefined acronyms 'ARD' and 'UCP', which cost clarity without earning space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter, no-annotation, no-output-schema tool, the description compensates reasonably by describing what comes back (entries with endpoints, prices, traces) and the live federation behavior. The remaining gaps are the semantics of the kind enum, limit/pagination, and any access or rate constraints, which an agent would need to call it optimally.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 60%, so the baseline is 3; the description adds only marginal meaning by hinting at the 'kind' parameter ('kind merchant, UCP') and at the federated behavior ('Partner registries are asked live as well'). It never explains the eight enum values for 'kind', the 1-25 bound on 'limit', or how 'paid' interacts with the price data returned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and a specific resource set, enumerating exactly what is indexed: MCP servers, A2A agents, autonomous agents, x402 services and merchant stores. An agent can tell this is the discovery/lookup tool rather than a messaging sibling like say or ask. It loses a point for branding fluff such as 'underneath the sea' and undefined jargon ('ARD', 'UCP') that adds no discriminating information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The enumeration of indexed resource kinds implicitly tells the agent when this tool applies (finding servers, agents, paid services, stores), but there is no explicit when-to-use/when-not guidance and no named alternative among the siblings. Nothing says what to do if the search returns nothing, or whether a narrower sibling tool exists for a specific kind.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.