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

Annotations already include readOnlyHint=true and destructiveHint=false. The description adds valuable context beyond these: 'No browser, no proxies, no login' (direct HTTP), pricing of $0.01/call paid via x402 (USDC on base), and the diff semantics that rely on a user-supplied previous stack.

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 concise sentences deliver the core function, behavioral constraints, and cost. The description is front-loaded with the main purpose and every sentence provides distinct value with no redundancy.

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 only 2 parameters, no nested objects, and a detailed schema, the description is sufficiently complete. It conceptually covers the return value ('exactly what was added or removed'), though with no output schema, a bit more detail on the response format could be beneficial, but it is not critical.

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?

The input schema descriptions cover both parameters fully, including the pipe-separated syntax for items and the default/max for maxConcurrency. The tool description only restates the diff concept without adding parameter-level detail, so it stays at the baseline.

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 uses specific verbs and resources: 'Detect a website's current technologies' and 'diff it against a previously-seen stack you supply'. It enumerates tech categories (CMS, ecommerce, analytics, etc.) and clearly distinguishes from the sibling tech-stack-detector by the diff capability.

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 explains that diffing requires a previously-seen stack supplied by the user, and indicates that bare domains just detect the current stack. However, it does not explicitly name alternatives like tech-stack-detector for when no previous stack exists, so the guidance is clear but not exhaustive.

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