well-011-sharescan

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

Goes well beyond the annotations (which only cover read-only/idempotent safety) by disclosing cost ($0.005 USDC via x402), the no-storage guarantee for hashed term lists, the 10 MB / https-only limits, unscanned-binary behavior, the return shape, and a no-warranty disclaimer. These are exactly the operational traits an agent must know before invoking.

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?

Dense but front-loaded: the one-line purpose and cost lead, then scope, limits, and caveats. Every clause carries information, though the telegraphic stacking of disclaimers ('A clean scan is not a clearance. As is, no warranty.') is compact to the point of terse.

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 compensates by stating the return format ('JSON hits with line numbers'). It covers cost, input limits, privacy, and safe-binary behavior. Minor gaps remain: it doesn't explain x402 payment/failure handling or what a partial/unscanned result means for a final verdict.

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 100%, so the baseline is 3, but the description adds real meaning: it names the concrete detector categories (emails, coordinates, IPs, AWS/GitHub/Slack/sk- keys, private keys, JWTs) that the boolean 'detectors' flag controls, and clarifies the salted-hash flow ('sent per call, never stored'). The only unmentioned item is max_words, already documented in the schema.

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+resource ('Scan text or an https text URL') plus the exact detection scope: user-supplied terms, hashed terms, and leak-shaped strings. An agent knows precisely what this tool does and what it looks for. No siblings exist, so no differentiation is needed.

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?

Frames the use case explicitly ('Pre-share leak check') and adds the boundary that binary URLs are listed as unscanned rather than errored. It also warns that a clean scan is not a clearance, which sets expectations. There are no alternative tools to route against, so no exclusion guidance is possible.

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