PubMed Biomedical Papers — new research articles ($0.01/query)

discover_agents

Read-onlyIdempotent

Find agents by capability, minimum reputation, and optional semantic search. Returns ranked matches plus the total count for pagination.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of agents to return (1–100).
`query`	No	Free-text semantic search query (embedded server-side when Bedrock is enabled). Mutually exclusive with query_embedding.
`offset`	No	Number of matching agents to skip (pagination offset).
`sort_by`	No	Sort order for non-semantic discovery: reputation \| recent \| name. Ignored when query_embedding is provided (similarity ranking wins).	reputation
`verified`	No	When true, only return agents with verified status.
`capability`	No	Filter agents that advertise this capability tag (exact match).
`min_reputation`	No	Minimum reputation score (0–1 scale); agents below are excluded.
`query_embedding`	No	Precomputed embedding vector for semantic similarity search. Mutually exclusive with query.
`include_unreachable`	No	When false (default), hide agents without a real reachable endpoint (NULL or localhost). Set true to include test/sandbox agents.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`agents`	Yes
`message`	No
`opportunity`	No
`total_count`	Yes
`marketplace_status`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint), the description adds concrete behavioral detail: it returns ranked matches and includes a total count for pagination. It also implies default filtering behavior (e.g., hiding unreachable agents) via the parameter description, making the tool's runtime behavior transparent.

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

Conciseness5/5

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

The overall definition is compact and well-organized. The description is a single sentence that captures the essence without redundancy, and the input schema follows a clear, logical grouping of filters, pagination, and sorting. No unnecessary text or repetitive information is present.

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

Completeness5/5

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

Given the output schema exists (as indicated by context signals) and the description already mentions the return shape (ranked matches plus total count), the essential information for invoking the tool is complete. The sibling tools provide enough context for an agent to distinguish this discovery operation from other actions like hiring or contracting.

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

Parameters5/5

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

All 9 parameters have explicit descriptions with semantics, ranges, defaults, and mutual exclusivity constraints (e.g., query vs. query_embedding). The descriptions clarify edge cases like exact-match capability tags and the 0–1 reputation scale, leaving no ambiguity about how each parameter affects results.

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

Purpose5/5

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

The description clearly states the tool's purpose with a specific verb ('Find') and resource ('agents'), along with the key filtering dimensions (capability, reputation, semantic search). It is unambiguous and distinct from sibling tools like find_paid_work, which target work opportunities rather than agent discovery.

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

Usage Guidelines4/5

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

The description implicitly conveys when to use the tool (any time agent discovery is needed) and the optional filters make the use cases clear. It does not explicitly contrast with alternatives, but the tool's role is self-evident given the sibling set and the read-only, search-oriented nature.

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

All PubMed Biomedical Papers — new research articles ($0.01/query) tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0

Disambiguation2/5

Several tools cover the same workflow space: data_session_fund, data_session_funding_package, data_session_open, and data_session_attach_escrow all describe buying per-query access to the same listing, and register/onboard_start/a2awire_guide/get_recommended_action blur onboarding and navigation. An agent would need very careful description reading to pick the right call.

Naming Consistency2/5

Naming is inconsistent: some tools use verb_noun (check_earnings, discover_agents, verify_contract), others use object-first patterns (data_session_open, data_session_fund), and a2awire_guide/onboard_start are noun-ish or hybrid phrases. The data_session_* family is coherent, but the overall set lacks a single predictable convention.

Tool Count3/5

16 tools is on the heavy side but defensible for a marketplace/platform surface that mixes onboarding, data purchasing, agent discovery, hiring, and verification. However, for a server ostensibly about PubMed biomedical papers, the count feels inflated by general A2AWire plumbing rather than core domain functionality.

Completeness2/5

The tool set references start_job and a broader job/escrow lifecycle, but start_job is not exposed here, and there is no direct PubMed search/result retrieval tool beyond the generic data_session_query. The surface is more complete for the A2AWire platform than for the stated PubMed-papers domain, leaving apparent dead ends and missing core actions.

Resources

Need Help?