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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered; the description adds genuinely new behavioral facts beyond that — per-dataset credit costs (13), fast/deep brief pricing (10/40), and that empty or unavailable datasets are free. It still omits what the response looks like and the credit-exhaustion failure mode, but the cost model is meaningful added context.

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 tightly packed sentences with no filler: the capability list comes first, the cost model second. The pricing clause is dense but each element (per-hit, brief, free cases) carries distinct decision-relevant information.

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?

With no output schema, the description should ideally hint at the shape of the returned datasets or the brief, and it does not. For a cost-incurring, non-idempotent call the pricing coverage is good, but the sibling ambiguity and absent return-value framing leave gaps an agent must guess at.

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 50% (company_domain and idempotency_key are documented in-schema; want and depth are bare enums). The description compensates by explaining that 'want' selects among independently statused datasets and that 'depth' (fast/deep) applies specifically to briefs and changes the price, which is semantics the enum alone does not convey.

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 specific verb and resource ('Enrich one company domain') and enumerates the concrete datasets it can return (profile, technologies, funding, relationships) plus the brief alternative, which is far more than a restatement of the title. However, it never distinguishes itself from close siblings like research_company or enrich, so an agent still has to infer which enrichment tool to pick.

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 single-domain scope ('one company domain') is implied as a usage boundary versus batch tools, and the pricing sentence implicitly warns the agent about cost. But there is no explicit when-to-use, when-not-to-use, or named alternative, so selection against research_company/enrich remains unguided.

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