Numbers Online — phone intelligence

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint. Description adds that the output is 'low-confidence', that verstat folds into risk signal, and that it's supplementary. No contradiction.

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?

Four sentences, each with distinct value: what the tool returns, its role, optional input usage. No fluff. Front-loaded with core purpose.

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?

Given parameters are well-described and output schema absent, the description adequately hints at output structure (spam signal, verstat passthrough, DNC signal). Could benefit from more explicit output typing, but overall complete for a risk signal tool.

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 covers both parameters 100%. Description adds 'loose input is normalized' for number, and explains that verstat is optional and folds into risk signal, enhancing understanding beyond raw 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 clearly states it returns a 'labeled, low-confidence risk read for an inbound caller' with specific outputs (spam signal, verstat passthrough, DNC signal). It distinguishes from siblings like dnc_check, line_type, phone_lookup by combining multiple signals and noting 'without a name dip'.

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?

Explicitly says it's 'a supplementary input to the agent's own policy, never a verdict on whether to accept or reject the call', guiding appropriate use. It also explains the role of verstat. However, it does not explicitly list when to use vs. alternative tools.

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?

The description goes beyond annotations by clarifying the data source (first-party preferences, not government registries), the meaning of each return value, and that absence of suppress is not consent. It also mentions a signed receipt. Annotations already declare readOnlyHint, openWorldHint, idempotentHint, which are consistent.

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 a single, well-structured paragraph that front-loads the core purpose and then adds necessary details. Every sentence contributes meaning without redundancy.

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?

Given the tool has only one parameter, no output schema, and comprehensive annotations, the description fully covers the tool's behavior, return values, and constraints. It is complete for an agent to use correctly.

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 input schema fully covers the single parameter 'number' with E.164 format and normalization details. The description does not add additional parameter semantics beyond what the schema provides, so a baseline score of 3 is appropriate.

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 clearly states the tool returns a do-not-contact signal for a phone number, specifying it's from first-party suppression preferences only. It distinguishes itself from sibling tools like caller_risk, line_type, and phone_lookup by focusing on DNC status.

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 explains the three possible return values (suppress, no_match, unknown) and their implications, and emphasizes it's an advisory input not asserting lawfulness. However, it does not explicitly compare to sibling tools or state when to use them instead.

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?

Annotations already indicate readOnly, openWorld, idempotent. Description adds that results are deterministic, free, and fast, providing behavioral context beyond annotations. No contradictions.

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?

Two sentences, front-loaded with key outputs and use case. Every sentence adds value without fluff. Highly concise and well-structured.

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?

Reasonably complete given simplicity, but lacks explicit output format or error handling information. Since no output schema exists, description should ideally specify return structure more precisely.

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 single parameter 'number' has 100% schema coverage with a clear description. The tool description does not add additional semantics beyond what the schema provides, so baseline score of 3 is appropriate.

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?

Description clearly states it returns deterministic fields (validity, line type, carrier, country, formatting) for a number. It distinguishes from paid dips and positions itself as a free, fast classification tool, differentiating from siblings like caller_risk or dnc_check.

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?

Explicitly suggests use 'before deciding to enrich', implying a preliminary check. Mentions it's free and fast, guiding when to choose it. Does not explicitly state when not to use or directly compare to siblings, but context is clear.

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?

The description adds significant behavioral context beyond the annotations (readOnlyHint, openWorldHint, idempotentHint). It clarifies the low-confidence, advisory nature of the data and explains the DNC signal is a first-party preference, not a government registry. No contradictions with annotations.

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 a single sentence that effectively conveys a lot of information. While it is somewhat dense, it avoids unnecessary words and is front-loaded with the main action. Could be slightly improved by breaking into bullet points for clarity.

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?

Without an output schema, the description effectively explains what is returned (validity, formatting, line type, etc.) and provides nuance on the DNC signal. It covers the key points for an intelligence tool, though it could elaborate on the interpretation of 'low-confidence' and the format of the bundle.

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 base is 3. The description adds some value by explaining how verstat is used ('fold it into the spam signal'), but does not significantly enhance understanding of the other parameters beyond their schema descriptions.

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 specifies a clear action ('Return a supplementary, low-confidence intelligence bundle for a phone number') and enumerates the exact data points returned. It distinguishes itself from siblings by emphasizing its advisory nature and that the agent retains routing decisions, though it does not explicitly name sibling tools.

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 states 'Advisory only — the agent keeps every routing and dialing decision,' which implies a context where the tool is supplementary. However, it provides no explicit when-to-use or when-not-to-use guidance, nor does it mention alternative tools like dnc_check or line_type that could be used instead.

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