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

Adds substantive behavior beyond the annotations (openWorldHint/readOnlyHint false): it costs 1 search credit, runs live against external public sources plus each business website, and takes 1 to 4 minutes. The only gap is failure/partial-result behavior on timeouts or exhausted credits, which is left implicit.

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?

Three tightly packed sentences, front-loading what the tool does, then cost, then latency/handoff. Every clause carries operational information; nothing is repeated from the title.

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 non-idempotent, credit-consuming, slow tool with no output schema, the description covers cost, latency, waiting strategy and the follow-up path. It is only slightly incomplete in not stating what the call returns immediately (e.g., that a searchId is produced) or what happens if credits run out mid-call.

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, but the description earns extra by explaining waitSeconds as a blocking alternative to polling and citing its 50-second ceiling and default-0 behavior in context. businessType and city add nothing beyond the schema examples, which is acceptable.

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 concrete verb and resource with explicit scope: 'Start a live search for one business type in one city', and adds what the search actually does (public listings plus per-website email/phone/social reads). This differentiates it from siblings like search_leads (reading results) and get_search_status (polling).

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-to-use routing: check search_leads first to avoid spending a credit, use waitSeconds to block here, or poll get_search_status instead, then read results with search_leads and the searchId. Alternatives and the condition selecting each are named.

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