numberbroom-mcp

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly reveals a non-obvious trait: calling this tool does not spend credits, which implies a read-only, non-consuming operation. It does not cover return format or authentication requirements, but for a 0-parameter read tool this covers the most important behavior.

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?

The description is two short sentences with no filler. The primary action is front-loaded, and the cost-related note is a single compact clause. Every word earns its place.

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 simple, parameterless read operation with no output schema, the description fully explains what the tool does, the account scope, and the key cost behavior. Nothing essential for an agent to invoke it 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?

The tool has zero parameters, so the baseline is 4 as per the rubric. The description adds no parameter-level meaning, but none is needed because the schema is empty and there is nothing to document.

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 states a precise action ('Check'), a specific resource ('remaining pre-paid API credit balance'), and the scope ('connected NumberBroom account'). It is clearly distinguishable from the only sibling, verify_phone_number, which obviously performs a different operation.

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?

The phrase 'Free to call — does not spend credits' clearly signals when to use this tool (when balance info is needed without consuming credits), but it does not explicitly mention an alternative or state a 'when not to use' condition. The context is clear enough, though exclusion guidance is absent.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond a basic operation statement by warning that a dead mobile still reports as mobile, so the agent must read isLikelyDisconnected rather than lineType. It also discloses billing edge cases, the DNC exclusion, and the need for an API key.

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?

The description is dense but every sentence earns its place: purpose and outputs, behavioral caveat, DNC exclusion, pricing with an important billing exception, and API key acquisition. It is front-loaded with the core purpose and uses a clear colon-delimited list for outputs.

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 one-parameter tool with no annotations and no output schema, this description is remarkably complete. It covers what the tool returns, the critical behavioral caveat about disconnected numbers, what it does not check, cost, billing on parse failure, and credential acquisition. Nothing required for correct invocation 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 coverage is 100% and the schema already describes the phone parameter format. The description adds meaningful scope by specifying 'single US phone number' and clarifies invalid-input handling by stating that a number failing to parse is not charged. This goes slightly beyond the schema's literal content.

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 and resource, 'Verify a single US phone number,' and then enumerates the concrete outputs: line type, carrier name, activity score, likely-disconnected flag, and TCPA litigator status. It is clearly distinct from the sibling get_credit_balance, which is about account balance rather than phone verification.

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?

The description makes the tool's scope and exclusions explicit: it verifies carrier-level data, does not check Do Not Call registries, and costs $0.20. It does not explicitly name an alternative tool for different use cases, but the sibling get_credit_balance is obviously unrelated, and the when-not guidance about DNC is clear.

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