Detect website tech stack

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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses significant runtime behavior: it 'Runs the Apify actor kantolabs/website-tech-stack-detector with your APIFY_TOKEN,' defines the per-site cost of $0.003, states 'failed or unreachable sites are free,' and explains that maxTotalChargeUsd is a hard spending cap. This gives the agent a clear picture of side effects, cost, and failure handling that annotations alone do not convey. No contradictions 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 multi-sentence and somewhat lengthy, but every sentence carries information: purpose, fingerprint count, use cases, read-only nature, cost, actor name, token, and spending cap. It is front-loaded with the core purpose, then details. It could be tightened (e.g., merging cost and actor lines), but it is not bloated or redundant. Minimum viable conciseness for the richness of information provided.

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 there is no output schema, the description adequately explains what the tool returns: 'technologies ... with versions and confidence.' It covers the full lifecycle: what it detects, when to use it, safety (read-only), cost, failure behavior, and execution mechanism (actor and token). The 5 parameters are all described in the schema, and the description adds usage nuance like batching. Nothing critical is missing for correct invocation.

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 100%, so the input schema already documents each parameter with defaults and constraints. The description adds value beyond the schema by explaining the cost model tied to urls ($0.003 per site), the billing to Apify account, and the purpose of maxTotalChargeUsd as a 'hard spending cap.' These operational details are not in the schema and help the agent reason about cost and limits. Baseline 3, but the extra context justifies a 4.

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 and resource: 'Detect the technologies a website runs on' and enumerates the categories (CMS, ecommerce, frameworks, analytics, ad tags, CDN, hosting, payment, marketing tools). It explicitly positions it against sibling tools by noting its niche ('website tech stack' detection) and mentions concrete use cases like lead qualification and competitor research, making the tool unmistakably distinct from audit_website_seo, check_website_traffic_rank, and similar 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 states specific scenarios: 'Use it for lead qualification, competitor research, sales prospecting or "what is this site built with?" questions.' It also provides operational guidance: 'Reads only the public page, one request per site,' warns about cost, and even recommends splitting large batches in the timeoutSecs parameter. Though alternatives aren't named, the use cases are explicit and sufficient for an agent to route correctly.

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