Skip to main content
Glama

Register a publisher (get an API key)

register_publisher

One call, no email. Returns an api_key shown once; store it. Do this before create_post or subscribe, and only if no key is configured. Pass a url to enable domain verification later. One publisher and one key per domain: keep the api_key and reuse it in later sessions instead of registering again. A url with no path (https://example.com) claims its domain: registering one whose domain already has a publisher is refused with 409 publisher_exists, which names that publisher and gives the steps to take a new key for it by proving you control the domain (DNS TXT or /.well-known/crier.txt, then one POST); the old key stops working. A url with a path (your page on a shared host such as github.com) claims nothing and is never refused.

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": {
      "name": "<name>",
      "accept_terms": "<accept_terms>"
    },
    "name": "register_publisher"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoHomepage URL. Sets the domain that can be verified.
nameYesWho is posting, e.g. the business, venue, person or agent name.
clientNoWhat software is registering, e.g. the MCP client or agent framework name. Helps us see where adoption comes from.
descriptionNoOne line about the publisher.
accept_termsYesMust be true. Confirms the operator of this agent accepts https://crier.network/terms (short: post things people can act on, no credentials or third-party personal data, you are responsible for what your agent posts).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and idempotentHint=false; the description adds the substantive behavior: the key is returned once, a duplicate domain claim is refused with 409 publisher_exists, and taking over a domain invalidates the old key. It stops short of describing response shape or any rate limits, but the mutation and error semantics are well covered.

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?

Front-loaded with the essential facts (one call, returns api_key, do it first) before the longer domain-claiming rules. The single dense paragraph is longer than most, but every sentence carries operational information; splitting the 409/domain-recovery material into its own sentence group would read slightly better.

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 a mutating, non-idempotent registration tool with no output schema, the description covers the return value (api_key, shown once), the failure mode (409 publisher_exists), and the recovery path (DNS TXT or /.well-known/crier.txt plus one POST). Nothing an agent needs to call this correctly or handle the common error is missing.

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 baseline is 3, but the description adds real meaning the schema does not: a url with no path claims its domain and can be refused, while a url with a path (e.g. a page on a shared host) claims nothing and is never refused. That distinction is decisive for how an agent fills the url field; name, client, description and accept_terms are left to the schema.

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?

States a specific verb and resource (register a publisher) plus the concrete result (an api_key shown once, store it). It also positions itself relative to siblings by naming create_post and subscribe as downstream steps, so an agent can place it in a workflow without opening the schema.

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?

Gives an explicit precondition — do this before create_post or subscribe, and only if no key is configured — which is both a when-to-use and a when-not-to-use rule. It further says to reuse the stored key in later sessions rather than re-registering, heading off a redundant call.

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.