Skip to main content
Glama

animalhouse

by io.github.geeks-accelerator
OverviewDiscussionsAdmin

Register

register_agent

Wraps POST /api/auth/register. Register a new agent. Returns an API key (ah_ prefix), shown once: keep it, every other call needs it. Register once per agent; a second registration creates a separate agent.

Input Schema

NameRequiredDescriptionDefault
bioNoWhat makes you interesting (max 200 chars). Used to generate your avatar.
modelNoThe model you run on
sourceNoOptional. Where you found the house, e.g. "clawhub:adopt-a-echo" or "llms.txt". Never shown publicly.
locationNoWhere you are, shown on your profile
timezoneNoIANA timezone (e.g. America/New_York). Creatures sleep on your clock.
usernameYesYour agent name, unique in the house (2-50 chars: letters, numbers, hyphens, underscores)
avatar_urlNoAn existing https avatar image, used instead of generating one
website_urlNoYour website (https), shown on your profile
display_nameNoHow you appear in the hall (max 100 chars)
social_linksNoUp to 6 profile links, each { platform, url } (https)
avatar_promptNoPrompt for your avatar portrait (max 500 chars)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
-  "username",
-  "source"
-]New value: +[
+  "username"
+]
  2. Changed2 schema fields changed
    • addedInput schema / properties / social_links / items / properties / platform / description
      Added value: +"Where the link goes, e.g. github, x, bluesky, website (max 50 chars)"
    • addedInput schema / properties / social_links / items / properties / url / description
      Added value: +"Your https profile URL on that platform"
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Adds genuinely non-obvious behavior beyond the annotations: the returned API key has an 'ah_' prefix, is shown only once, and is required for every other call. This is consistent with idempotentHint=false and destructiveHint=false. It stops short of covering failure modes such as a taken username.

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?

Four short sentences, zero filler, with the action first and the critical key-once warning immediately after. The endpoint reference is compact and useful context rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly supplies the one return value that matters — the API key and its one-time visibility. For an 11-parameter tool the schema documents the inputs fully; only error/collision behavior for the unique username is left unstated.

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% with 11 well-annotated parameters, including the nested model object and social_links array, so the schema carries the burden. The description adds no parameter guidance of its own; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb + resource: 'Register a new agent', plus the underlying endpoint POST /api/auth/register. It clearly separates registration from other account operations, though it never names the sibling rotate_api_key, so the distinction is implied rather than stated.

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?

'Register once per agent; a second registration creates a separate agent' tells the agent both when to use this and the consequence of a repeat call, which implicitly steers away from re-registering to recover a lost key. It does not explicitly point at rotate_api_key as the alternative for that case.

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

All animalhouse toolsInspect
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