Teardrop

Discover Agents

discover_agents

Read-only

Find opt-in remote A2A agents, published tool capabilities, endpoints, and public reputation status.

Use when: Use before delegate_to_agent when a specialist agent is needed but its URL is unknown.

Limitations: Discovery is read-only and does not add an agent to the org allowlist; delegate_to_agent remains authoritative.

Alternatives: delegate_to_agent

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	No	Optional search across agent name, organization slug, or published tool name
`limit`	No	Maximum number of agents to return

Output Schema

TableJSON Schema

Name	Required	Description
`count`	Yes
`agents`	Yes
`generated_at`	Yes
`registration_endpoint`	No	Endpoint where an organization can publish its own A2A endpoint.
`registration_benefits_url`	No	Machine-readable registration benefits, requirements, and non-guarantees.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 4, 2026

addedOutput schema / properties / registration_benefits_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Machine-readable registration benefits, requirements, and non-guarantees.",
+  "title": "Registration Benefits Url"
+}

addedOutput schema / properties / registration_endpoint

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Endpoint where an organization can publish its own A2A endpoint.",
+  "title": "Registration Endpoint"
+}

Changed3 schema fields changedSep 4, 2026

changedInput schema / properties / q / description

Previous value: -"Optional search across agent name and organization slug"New value: +"Optional search across agent name, organization slug, or published tool name"

addedOutput schema / $defs / DiscoveredAgent / properties / registered_at

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "UTC timestamp when the organization first registered its A2A endpoint",
+  "title": "Registered At"
+}

addedOutput schema / $defs / DiscoveredAgent / properties / tool_names

Added value: +{
+  "description": "Names of up to 20 active published tools exposed by the agent organization",
+  "items": {
+    "type": "string"
+  },
+  "title": "Tool Names",
+  "type": "array"
+}

AddedAug 31, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description reinforces this while adding more: discovery 'does not add an agent to the org allowlist' and 'delegate_to_agent remains authoritative.' This is useful behavioral context beyond the structured annotation.

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 compact, with a clear front-loaded purpose followed by labeled 'Use when,' 'Limitations,' and 'Alternatives' sections. Each section earns its place and avoids redundant or filler content.

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, the read-only annotation, and the explicit routing to delegate_to_agent, the description is sufficiently complete. It covers purpose, usage timing, side-effect boundaries, and alternatives without needing to explain return values.

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% for the two optional parameters (q and limit), so the schema already documents parameter meaning. The description adds no additional parameter-level detail, so the baseline score of 3 is appropriate.

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 a specific action ('Find') on a specific resource ('opt-in remote A2A agents, published tool capabilities, endpoints, and public reputation status'). It distinguishes the tool from name/tautology and references its intended role relative to delegate_to_agent.

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

Usage Guidelines5/5

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

The description explicitly says when to use it: 'before delegate_to_agent when a specialist agent is needed but its URL is unknown.' It also gives an exclusion by noting discovery does not add an agent to the allowlist, and names delegate_to_agent as the alternative.

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

All Teardrop tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?