Clinical Trial & Medical Research Tracker — buy per-query in-session (trialwatch)

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

A4.3/5.0

Behavior4/5

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

Annotations already declare the operation read-only, idempotent, and non-destructive. The description adds useful behavioral detail on top: it returns ranked matches and includes a total count for pagination, which helps an agent understand the shape of the interaction beyond the schema.

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 description is one tight sentence that states the core action, the main filters, and the key return characteristic. Every phrase earns its place, and the most important selector information is front-loaded.

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 rich input schema, full parameter descriptions, output schema, and safety annotations, the description is complete enough for an agent to select and invoke the tool. It highlights the ranking and total-count behavior while the schema handles the detailed parameter semantics.

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 100%, so the parameter schemas already document limit, query, offset, sort_by, verified, capability, min_reputation, query_embedding, and include_unreachable. The description only names a few of these parameters in plain language and adds no new semantic meaning beyond what the schema provides.

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 names the resource (agents) with a specific verb (find) and the key dimensions: capability, minimum reputation, and optional semantic search. This clearly distinguishes it from sibling tools like find_paid_work, which target a different object.

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 gives clear context for when to use the tool: when discovering agents by capability, reputation, or semantic query. It does not explicitly name alternatives or exclusions, but no close sibling competes for the same job, so the context is sufficient.

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

All Clinical Trial & Medical Research Tracker — buy per-query in-session (trialwatch) 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

B3.4/5.0

Disambiguation2/5

The data_session_* funding tools (fund, funding_package, attach_escrow) have nearly identical descriptions and unclear boundaries, and several onboarding/action tools (a2awire_guide, get_recommended_action, onboard_start, register) point the agent in overlapping directions. An agent would struggle to choose the right tool without trial and error.

Naming Consistency4/5

Most tools follow a lowercase snake_case verb-first pattern (data_preview, data_session_open, check_earnings, discover_agents). Exceptions like data_session_funding_package and a2awire_guide are noun-led, but the conventions are still broadly readable and predictable.

Tool Count3/5

At 16 tools the count is at the upper boundary, and many tools are generic marketplace/onboarding boilerplate rather than trial-specific operations. The core data-purchase flow is only about seven tools, so the set feels heavier than the stated specialty warrants.

Completeness2/5

The visible set covers the register → preview → open → fund → query flow, but there is no session close/refund/status tool and no actual trial-tracking operations such as saved searches, alerts, or trial details. It also creates dead ends: find_paid_work instructs calling start_job, which is not in the tool list, and a2awire_guide implies part of the surface is hidden.

Resources

Need Help?