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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses that nothing is installed or run, that the package name and version are sent to its registry, that results are cached for 24 hours, that a fresh scan takes about a minute and runs one at a time, and that findings are content-free (ids, paths, hashes only).

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?

Front-loaded with the core action, then safety posture, return shape, external side effects, and caching. Every sentence carries distinct information with no restatement of the title or schema.

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 still enumerates the verdict values, the finding fields, and the permalink, and covers latency, rate limits, and data-sharing. An agent has everything needed to call it and interpret the result.

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% for the single ref parameter, so the schema already documents the accepted syntax. The description adds only the framing that the ref must resolve to a published package, which is useful but marginal against a fully documented 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?

Specific verb and resource: 'Download one published package and run static analysis on its code.' The ref formats (npm/pypi/github) and the phrase 'one published package' implicitly separate it from scan_skill and scan_mcp_config, but no sibling is named explicitly.

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 by the described scope ('one published package', static analysis only), and the 24-hour reuse note hints at repeat-call behavior. However, the description never states when to prefer this over lookup_verdict or scan_skill, nor any exclusions.

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