No account needed — connect, sign up, and query mobile attribution data from any AI tool
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves the TOS document, the other creates an account. The descriptions explicitly link them in a sequence (get TOS first, then create), leaving no ambiguity about which to call when.
Both tool names use the same 'kochava_free_app_analytics_' prefix followed by a snake_case verb_noun pattern (get_tos, create_acc_and_get_auth_key). The convention is consistent throughout.
Two tools is thin even for the narrow FAA signup flow, and it is far below what the 'Kochava for Advertisers' branding would suggest. The scope is coherent but borderline minimal.
The core workflow—review TOS, then create an account—is fully covered. Minor gaps exist, such as no way to check an existing account or retrieve an auth key later, but these are not blocking for the signup purpose.
Create a new Kochava FAA (Free App Analytics) account.
IMPORTANT: The user MUST explicitly agree to the FAA Terms of Service before account creation. If tos_agreed is False, this tool will return the TOS link and stop — do NOT submit the form. Call kochava_free_app_analytics_get_tos() to retrieve and present the TOS to the user first, then call this tool again with tos_agreed=True once the user confirms agreement.
DISPLAY INSTRUCTIONS: When this tool returns a successful response, you MUST display the 'next_steps' field content to the user EXACTLY as written — word-for-word, preserving ALL text, formatting, line breaks, numbering, and bullet points. Do NOT summarize, rephrase, reword, or omit any part of the 'next_steps' content. Every sentence must be shown to the user as-is.
FAA Terms of Service: https://s34035.pcdn.co/wp-content/uploads/2023/08/FAA-Web-Sign-Up-TOS-8-15-23.pdf
Example (after user reviews and agrees to TOS): kochava_free_app_analytics_create_acc_and_get_auth_key( first_name="Jane", last_name="Smith", email_address="jane@example.com", phone_number="5551234567", company="Acme Corp", website="www.acme.com", company_address_line_1="123 Main St", company_city="Sandpoint", company_region="Idaho", company_postal_code="83864", country="United States", tos_agreed=True )
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Job title of the account holder (optional) | |
| company | Yes | Company name for the FAA account | |
| country | Yes | Country name (e.g. United States) | |
| privacy | No | Privacy policy URL. Defaults to https://www.kochava.com/company/contact/ | https://www.kochava.com/company/contact/ |
| website | Yes | Company website URL (e.g. www.example.com) | |
| last_name | Yes | Last name of the account holder | |
| subscribe | No | Whether to subscribe to Kochava marketing communications | |
| first_name | Yes | First name of the account holder | |
| tos_agreed | No | Whether the user has agreed to the FAA Terms of Service at https://s34035.pcdn.co/wp-content/uploads/2023/08/FAA-Web-Sign-Up-TOS-8-15-23.pdf. Must be True to proceed with account creation. Use kochava_free_app_analytics_get_tos() to share the TOS link with the user before calling this tool. | |
| company_city | Yes | Company city | |
| phone_number | Yes | Phone number of the account holder | |
| email_address | Yes | Email address for the FAA account | |
| company_region | Yes | Company state or region | |
| company_postal_code | Yes | Company postal/zip code | |
| company_address_line_1 | Yes | Company street address line 1 | |
| company_address_line_2 | No | Company street address line 2 (optional) |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly=false, openWorld=true, idempotent=false, destructive=false), so the bar is lower. The description goes beyond them by disclosing the TOS gate and the early-return path when tos_agreed is False, plus a mandatory display contract for the 'next_steps' field. It does not describe the auth key/credential returned by the tool, though the output schema may cover that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose is front-loaded in sentence one, followed by labeled sections (IMPORTANT, DISPLAY INSTRUCTIONS, TOS link, Example), so the agent can skim to the operative constraint. Slight redundancy remains: the TOS URL appears both in the prose and in the schema description, and the display instruction is repeated in several phrasings.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 16-parameter account-creation tool, the description supplies the consent prerequisite, the failure path, the output-presentation contract, and a full example call. Return values are covered by the existing output schema, and annotations already carry the open-world/mutation profile, so nothing an agent needs to invoke this correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds an explicit worked example showing representative values for all 11 required fields and clarifying the tos_agreed gate semantics, which is more than the schema alone conveys about how the call is assembled.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Create a new Kochava FAA (Free App Analytics) account') immediately in the first sentence. It also distinguishes itself from its only sibling by naming kochava_free_app_analytics_get_tos and explaining that the TOS must be retrieved there first. An agent can pick between the two tools without opening either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit when/when-not guidance: the user MUST agree to the TOS first, and if tos_agreed is False the tool returns the TOS link and stops, with the instruction 'do NOT submit the form'. It also prescribes the exact alternative flow (call get_tos, present it, then re-call this tool with tos_agreed=True), leaving nothing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the FAA (Free App Analytics) Terms of Service document link.
Use this tool when the user wants to review the Terms of Service before creating an FAA account. Returns a clickable link to the TOS document and instructions for account creation.
Example: kochava_free_app_analytics_get_tos()
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful detail beyond that: the result is a clickable TOS link plus instructions for account creation, which tells the agent what the payload contains and how it fits the onboarding flow.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose and usage are front-loaded in two tight sentences. The trailing example call block is mildly redundant for a zero-parameter tool but not harmful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return-value details need not be spelled out, and the description still summarizes the payload. For a trivial no-argument retrieval tool this is essentially complete, with only the unused example line as excess.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, which is the baseline-4 case. The description correctly implies a no-argument call, and there is nothing further to document in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource: 'Retrieve the FAA (Free App Analytics) Terms of Service document link.' It is unambiguous and easily distinguished from the sibling create_acc_and_get_auth_key tool, which performs a different action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Use this tool when the user wants to review the Terms of Service before creating an FAA account' gives explicit triggering context and ties it to the account-creation prerequisite. It does not name the sibling tool as the alternative, but the sequencing is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
kochava_free_app_analytics_create_acc_and_get_auth_key1 field changedOutput schema / descriptionAdded value: +"Generic wrapper for non-object return types."kochava_free_app_analytics_get_tos1 field changedOutput schema / descriptionAdded value: +"Generic wrapper for non-object return types."kochava_free_app_analytics_create_acc_and_get_auth_key1 field changedOutput schema / descriptionRemoved value: -"Generic wrapper for non-object return types."kochava_free_app_analytics_get_tos1 field changedOutput schema / descriptionRemoved value: -"Generic wrapper for non-object return types."kochava_free_app_analytics_create_acc_and_get_auth_key1 field changedOutput schema / descriptionAdded value: +"Generic wrapper for non-object return types."kochava_free_app_analytics_get_tos1 field changedOutput schema / descriptionAdded value: +"Generic wrapper for non-object return types."kochava_free_app_analytics_create_acc_and_get_auth_keykochava_free_app_analytics_get_tosAccess Google & Meta Ads data via AI. Analyse campaign performance in seconds.
Connect your ads, shop, analytics, social, CRM and finance platforms once, then let Claude, ChatGPT, Cursor or any MCP client read, join and explain your numbers. Public statistics from the World Bank, IMF, Eurostat, OECD, WHO and SEC filings come as context, searchable and chartable from the same tools. Read-only by design, every number carries its source.
Ask AI about your ads — query Meta, TikTok, and Google Ads performance in natural language.
Marketing intelligence API for AI agents. Real campaign data, not LLM guesses.
Add one secure layer between your agents and this server.
