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

Annotations already establish read-only, idempotent, closed-world behavior, so the bar is lower, and the description still adds real substance: Spurvik does not mark content, withSpurvik and spurvikMiddleware log the call and attach an HMAC receipt, and hooks fire only when supplied. It also clarifies that the signed trailer is not itself an Article 50(2) machine-readable mark, which prevents a costly misinterpretation. It does not say what the explanation returns (text, snippet, link).

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?

Purpose is front-loaded in the first sentence and each subsequent sentence adds a distinct fact about hook behavior or legal scope. The negative framing ('does not mark content' and 'not, by itself, an Article 50(2) machine-readable mark') is somewhat repetitive, but both disclaimers carry weight.

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 one-parameter explainer with no output schema, the description covers the mechanism (hooks, withSpurvik/middleware, HMAC receipt), the opt-in nature, and the legal boundary. The main gap is what the tool actually returns to the caller, which matters for an 'explain' tool.

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 0% for the single 'surface' parameter, so the description has to compensate. It does partially by naming marking.text and marking.media, which map onto the enum values, but it never explains what 'surface' selects or when the 'both' option is appropriate.

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 first sentence gives a specific verb and target: 'Explain how to plug your own Article 50(2) marking into marking.text or marking.media.' The follow-up 'Spurvik does not mark content' sharply bounds what the tool is not, so an agent knows this is an explainer about hook integration rather than a marking action. It stops short of naming how it differs from siblings like spurvik_explain_receipt or spurvik_setup_snippet.

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?

Usage is implied rather than stated: 'A hook runs only when you supply one' and 'The signed text trailer is an application-level binding you can opt into' tell the agent these are opt-in mechanisms, which hints at when this tool matters. There is no explicit 'call this when...' instruction and no exclusion pointing to an alternative tool.

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