Skip to main content
Glama

Register agent

register_agent

Add an agent to the registry by URL — an A2A card, an MCP endpoint or a bare domain, yours or one you found. The hub crawls it itself (card, handshake, tools, access, price) and lists only what it measured; nothing in the submission is trusted. Use it when search_agents and verify_endpoint do not know the URL; follow up with submission_status. Unsigned, no account, safe to repeat (repeats are rate-limited, not duplicated). Returns the queue state and when it will be looked at.

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": {
      "url": "<url>"
    },
    "name": "register_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesWhere the agent lives: an A2A agent card, an MCP endpoint, or a bare https domain
kindNoWhat the URL is, if you know; omit and the hub finds out

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / kind / description
      Added value: +"What the URL is, if you know; omit and the hub finds out"
    • addedInput schema / properties / url / description
      Added value: +"Where the agent lives: an A2A agent card, an MCP endpoint, or a bare https domain"
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the actual mechanism: the hub crawls the target itself (card, handshake, tools, access, price) and "nothing in the submission is trusted," so an agent knows submitted metadata is not what gets listed. It also discloses rate limiting on repeats and the return shape ("the queue state and when it will be looked at"). The only mild tension is that "safe to repeat" sits next to idempotentHint=false, but this is reconcilable: repeats are not duplicated yet still consume queue/rate-limit effects.

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?

Purpose, trigger, exclusions, follow-up, and return value are front-loaded across four dense sentences with no filler. The heavy parenthetical packing ("card, handshake, tools, access, price") costs a little readability, but nothing is redundant.

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?

For an open-world write with two parameters and no output schema, the description covers what an agent needs: what to pass, when this tool rather than its siblings, what happens server-side, what comes back, and which tool to call next. Nothing material is left for the agent to infer.

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

Parameters4/5

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

Schema coverage is 100%, so the field meanings are already documented and 3 is the baseline. The description still adds two useful semantics: the URL may point at a bare domain as well as a typed endpoint, and the target may be "yours or one you found," i.e. third-party registration is permitted. It stops short of adding format examples or precedence rules.

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 gives a specific verb and resource ("Add an agent to the registry") and immediately scopes what counts as the target: an A2A card, an MCP endpoint, or a bare domain. It also distinguishes the tool from search_agents and verify_endpoint by saying it exists for URLs those tools do not already know.

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?

It gives an explicit trigger ("Use it when search_agents and verify_endpoint do not know the URL") and an explicit follow-up path ("follow up with submission_status"). It also states preconditions an agent would otherwise have to guess: unsigned, no account required, and safe to repeat.

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.