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

The description adds significant behavioral context beyond the annotations. It discloses that the tool is free and anonymous (not in annotations), describes the return value (signed verdict) and its verifiability, explains freshness indicators (corpus contradiction and older rules version), and clarifies the meaning of a miss. This aligns with and enriches the openWorldHint and readOnlyHint annotations without contradiction.

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 concise and well-organized, with the core purpose front-loaded in the first sentence. Each sentence adds meaningful information (usage timing, input types, return details, miss semantics) with no fluff. While it is a single paragraph of moderate length, every part contributes to agent understanding, so it is appropriately sized.

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 the tool has only one parameter, rich annotations, and an existing output schema, the description is remarkably complete. It covers what the tool does, what to pass, what to expect in return (including freshness details), and the meaning of a miss. An agent can correctly invoke this tool and interpret the response without ambiguity.

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 schema already describes the subject parameter with 100% coverage, including an example. The description goes further by enumerating the valid input forms (package identity, MCP server URL, or sha256 hash) and noting the optional 'sha256:' prefix, which is not in the schema. This adds practical guidance that helps the agent format the input correctly.

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 clearly states the tool's purpose: to ask whether anyone has already attested an artifact. It specifies the resource (attestation) and provides clear guidance on input types (package identity, MCP server URL, or hash). It differentiates from siblings by emphasizing it is free, anonymous, and should be used before scanning – making it distinct from the scan_* and check_lockfile tools.

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 gives explicit timing guidance ('BEFORE you install it or pay to scan it') and clarifies the tool is free and anonymous, which implies using it as a pre-check. It also explains that a miss is not a verdict, preventing misuse as a safety check. However, it does not name specific alternative tools or explicitly state when not to use it beyond the pre-scan context, so it is strong but not exhaustive.

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