Agent Router

discover_agents

Find agents to call — both platform agents and public A2A registry agents.

Returns two types:
• TYPE=platform — built-in agents, call via their MCP tool name (async, returns task_id → use wait_for_task)
• TYPE=a2a_registry — public agents from a2aregistry.org, call via a2a_call_agent(agent_url=ENDPOINT, message='...') (sync, returns immediately)

Registry agents are filtered by the registry's own is_healthy flag.
Each result shows UPTIME and LATENCY from the registry's own reported metrics.

Free.

Args:
    query: Keywords to filter by capability (e.g. 'weather', 'web scraping', 'research'). Leave empty to browse top agents.
    limit: Max results to return (default 10, max 25).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

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

First observedJun 16, 2026

TDQS

A4.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It discloses async vs. sync behavior, filtering by is_healthy, and that results include uptime/latency metrics. It also notes the tool is free. It doesn't mention edge cases like pagination limits beyond the max 25 or error handling, but it covers the key behavioral traits an agent needs to know before calling.

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?

The description is longer than minimal but well-structured with bullet points and clear sections for each type. It is front-loaded with the purpose and immediately provides actionable calling details. Every sentence adds value, though it could be tightened slightly without losing information.

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?

The tool has an output schema (though not shown), and the description explains the two result types, their calling conventions, and the metrics shown. Given the complexity of handling two distinct agent types, the description covers everything an agent needs for correct invocation and follow-up. No obvious gaps.

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?

Schema description coverage is 0%, and the description fully compensates. It explains that 'query' filters by capability with examples, and that empty queries browse top agents. It specifies 'limit' default (10) and max (25). This adds significant meaning beyond the raw schema, making parameters self-explanatory.

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 uses the specific verb 'find' and resource 'agents', clearly stating the tool discovers both platform and A2A registry agents. It distinguishes itself from siblings like a2a_call_agent by specifying it's for discovery, not calling. The two distinct result types are clearly named and described.

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?

Explicitly states when to use this tool (to find agents) and provides distinct calling instructions for each type: platform agents via their MCP tool name with wait_for_task for async handling, and registry agents via a2a_call_agent with the agent URL. This routes the agent to the correct next step and implies the tool is a precursor to those actions.

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

All Agent Router 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

C2.7/5.0

Disambiguation3/5

Several tools overlap in purpose, particularly the research/analysis agents (constructivecritic, firstprinciplesanalyst, scientificresearchagent, researchagent) and the three reasoningdelegation agents, which differ only by effort level. Some tools like 'exploitagent' and 'testagent' have vague descriptions that don't clarify distinct roles. However, many tools are clearly distinct (e.g., campbuddy vs. smart_fridge___nutrition), and the core router tools (discover_agents, a2a_call_agent, wait_for_task) are well-defined.

Naming Consistency2/5

Naming is inconsistent: some tools use snake_case (a2a_call_agent, discover_agents, wait_for_task) while most others are camelCase or concatenated lowercase (browsernavigationagent, campbuddy, reasoningdelegationhigh). There's also odd naming like 'smart_fridge___nutrition' with triple underscore, and simple names like 'testagent' and 'exploitagent'. No consistent convention exists across the set.

Tool Count4/5

With 24 tools, this is near the upper limit but still reasonable for an agent router that hosts many pre-defined specialized agents. The core router functions (discover, call, wait) are supplemented by a diverse set of agent tools. It's borderline heavy but each tool represents a distinct agent or action, so it's acceptable.

Completeness4/5

The router functionality is well-covered: discovery (discover_agents), synchronous calling (a2a_call_agent), asynchronous handling (wait_for_task), and skill lookup (search_skills/get_skill) for extension. Missing are explicit cancellation or task management tools, but core workflows are supported. The presence of domain-specific agents (campbuddy, silpo_home_restaurant) doesn't detract from router completeness.

Resources

Need Help?