Find a phone number (most expensive)

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

Beyond the readOnlyHint annotation, the description discloses critical behavioral traits: it is billable with specific cost ($0.4 per phone found), a miss is free, it is roughly 20x an email lookup, and it is not to be used speculatively. It also instructs reading cost.amount_charged in every response, adding operational detail not covered by annotations. No contradiction 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 efficiently structured and front-loaded: it starts with the core purpose, then the cost and usage warnings, and finally the alternative. Every sentence provides actionable information—cost, comparison, and constraints—with zero fluff. It is appropriately sized for a tool with significant cost and misuse risk.

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 an output schema (mentioned in signals) and complete parameter documentation, the description is thorough. It covers purpose, cost, when to use, and when not to use, and directs to get_balance for pricing and to start_bulk_job for approved lists. The only potential gap—return format—is covered by the output schema. Nothing essential is missing for an agent to call it 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 covers all 7 parameters with full descriptions (100% coverage), so the baseline is 3. The description does not add parameter-specific semantics beyond what the schema already provides; it only mentions high-level usage context. It does not, for example, explain which parameter combinations are preferred, though the schema descriptions already cover that. Thus, the description adds marginal value over 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 clearly states the tool's purpose: 'Find a phone number for one person.' It uses a specific verb ('Find') and resource ('phone number'), and distinguishes itself from siblings by explicitly noting it is the 'MOST EXPENSIVE OPERATION HERE' and comparing cost to email lookup. This makes it unambiguous what the tool does and how it differs from alternatives.

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 provides explicit when-to-use and when-not-to-use guidance: 'Do not call it speculatively or across a list; confirm with the user first, and only for people they have already qualified. Use start_bulk_job for an approved list.' It also directs users to call get_balance for real pricing and to check cost.amount_charged, giving clear decision criteria for selecting this tool versus bulk alternatives.

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