search_leads

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

Annotations (readOnlyHint: false, idempotentHint: false, openWorldHint: true) are present; the description goes well beyond them by disclosing credit consumption ('CONSUMES SEARCH CREDITS on every call'), the side effect of each call starting a separate job, the API key requirement, and the additional AI credit cost of useAI. This is exactly the behavioral context an agent needs to avoid costly mistakes.

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?

Every sentence earns its place. The description is front-loaded with the most critical fact (async), then covers the polling workflow, sibling differentiation, cost warning, retry warning, auth, and AI-credit nuance — all in six tight sentences with strong formatting (caps, line breaks) that scannable. Zero fluff.

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 tool that starts an async job with no output schema and non-trivial side effects, the description is thorough: it explains the full request lifecycle, how to obtain results, when to use alternatives, billing implications, and auth prerequisites. Given the absence of an output schema and the tool's complexity (nested filters, async pattern), nothing significant is left undocumented.

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%, so the baseline is 3. The description earns a 4 by enriching the useAI parameter semantics: 'Setting useAI additionally spends AI credits to enrich and score the results as they arrive' — adding cost and timing context not in the schema. It also clarifies query's role in the async flow, though it stops short of documenting nested filter structure, which is handled well enough by 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 precise verb+resource+outcome: 'Start an AI lead-search job and return its jobId immediately.' It immediately distinguishes itself from sibling tools by noting the async nature ('results are not in the response') and later contrasts with 'list_leads for ones already saved.' This clearly differentiates it from list_leads, get_search_job_status, and other siblings.

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 guidance ('Use it to find NEW leads; use list_leads for ones already saved'), a full workflow ('Poll get_search_job_status with the jobId until it reports completion, then read the leads with list_leads'), and a warning against misuse ('do not retry it as a way to check progress'). This is model-user-nudging at its best.

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