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

The annotations already declare the safety profile (readOnlyHint false, destructiveHint false, openWorldHint false), so the description only needs to add operational context. It does add two genuinely useful facts beyond the annotations: an active plan is required, and subordinate OTHERTECHS filters do not consume additional primary report slots — quota behavior an agent could not otherwise infer. It stops there, disclosing nothing about pagination, rate limits, or what the JSON payload looks like.

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 short sentences, front-loaded with purpose before the prerequisite and the filter caveat; nothing is redundant. The single weak spot is the all-caps OTHERTECHS, which is slightly noisy without a matching schema field name of that casing.

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?

A 23-parameter query endpoint with 9% schema coverage and no output schema needs far more description than three sentences to be safely callable — the semantics of most filters and the shape of the returned lookup are unaddressed. The plan requirement and quota note are the right kind of content but cover only a fraction of what is missing.

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 9% across 23 parameters; only 'tech' and 'otherTechs' carry any documentation. The description reinforces the tech/otherTechs relationship, which is helpful, but the other 21 filters (since, country, spend, offset, bwRank, aiMaturity, etc.) get no meaning in either the schema or the description, so the coverage gap is largely uncompensated.

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 ('List API JSON lookup for websites') plus the scoping filter ('using a primary technology'), which tells an agent what the call returns and what the required axis is. It falls short of a 5 because it never differentiates itself from the many sibling list/ask/domain endpoints beyond the technology filter wording.

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 one real prerequisite ('Requires an active BuiltWith plan') and one usage rule for composed filters (OTHERTECHS are subordinate, not primary). It never says when to choose this over ask-api or the x402 variants, so the alternatives decision is left implicit.

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