Skip to main content
Glama

rocketsloth

by ai.rocketsloth

Apply as a Publisher

apply
Idempotent

Call this first after connecting. Connecting the MCP server is not an application. Requires site_url (http/https; need not be live yet), contact_email, publisher_name (the site owner's name — not your agent name), and agent_name; description is optional. Humans can sign up at https://rocketsloth.ai/signup. Returns an application token (at_...). Call integration immediately with it. Rocket Sloth never asks for payment card, bank account, government ID, or health information in chat. No authentication required; rate limited per IP.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
site_urlYesThe publisher site to monetize, as an http or https URL (e.g. https://example.com). Need not be live yet — apply now, integrate while you build; full demand starts once the site is live with the tag.
agent_nameYesYour name (the agent/operator applying on the publisher's behalf), e.g. 'claude-code'.
descriptionNoOptional short description of the site or its content.
google_emailNoOptional. The email address that will receive Google's Ad Manager invitation later in the process; it must belong to a Google account the site owner can sign in to. Defaults to contact_email when omitted.
contact_emailYesA contact email for the account. Used as the account login.
publisher_nameYesThe site owner's name for the publisher account (e.g. 'Jane Doe'), provided with the owner's consent — used only to create the account and its Google Ad Manager invitation. Not your agent name.

TDQS

A4.1/5.0
Behavior4/5

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

The annotations already declare idempotentHint=true and destructiveHint=false, and the description complements this with no-auth required, rate limiting per IP, and a promise that the service never asks for sensitive data in chat. It also discloses the return shape (an at_... application token) without contradicting the annotations.

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 but tightly packed: ordering, non-obvious parameter semantics, human signup fallback, next-step routing, security note, and rate limits. It is front-loaded with 'Call this first after connecting...' and each sentence contributes useful information without rambling.

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?

There is no output schema, yet the description tells the agent it receives a token, must call integration next, needs no auth, is rate limited, and that it should not concern itself with sensitive data. The only absent element is what to do after an application already exists, but that is covered by sibling tools and not necessary for a run-once introductory tool.

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?

The schema covers 100% of parameters, so the baseline is 3. The description adds only minor semantic hints (http/https URL not yet live; publisher_name is not agent_name), both of which the schema already provides. It omits google_email entirely, but the schema documents it clearly, so no deficiency at baseline.

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 explicitly states the action (apply as a publisher), positions it as 'Call this first after connecting,' and clarifies that connecting the MCP server alone is not an application. This makes the tool's purpose distinct from both the generic 'apply' name and sibling tools like 'integration' or 'application_status'.

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?

The description explicitly routes usage: 'Call this first after connecting,' then 'Call integration immediately with it.' It clearly instructs when to use the tool and what to do next. It lacks explicit 'do not use when...' exclusions, but as a one-time-first-step tool it is well-specified.

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

All rocketsloth toolsInspect
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

A4.4/5.0
Disambiguation5/5

Each tool has a distinct purpose and clear descriptions. Names like 'reclaim' and 'recover' refer to different operations, and 'ad_settings' vs 'reporting' are easily separable. No overlapping functions are apparent.

Naming Consistency3/5

Tool names mix nouns (account, payments, video) and verbs (apply, ask, reclaim) and use inconsistent naming conventions (snake_case for compound names like ad_settings, but single words elsewhere). There is no uniform verb-noun pattern or prefix.

Tool Count5/5

14 tools is a reasonable and comprehensive set for a publisher/ad platform covering onboarding, account management, ads, reporting, payments, subscriptions, video, and recovery. It is neither sparse nor bloated.

Completeness5/5

The tool set covers the full lifecycle from application (apply, application_status) through integration (integration, checklist), account management (account, ad_settings), monetization (reporting, subscriptions, video), and recovery (reclaim, recover). No obvious gaps for the stated domain.

Resources