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

Annotations already disclose read-only, open-world, and idempotent behavior; the description adds the cost ('Costs $2 per call'), which is a behavioral trait not covered by annotations. No 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?

Two sentences that are front-loaded with the purpose. Every clause earns its place: the action, resource, ecosystems, value proposition, and cost. No redundant or fluff content.

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 tool with a nested source object and no output schema, the description covers the core purpose, supported ecosystems, cost, and typical use case. It does not explain return format, but the lack of output schema reduces that obligation. Adequate for selection and invocation.

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 description coverage is 50% (previous_scan_id described in-schema; source not). The description adds meaning by enumerating supported ecosystems (npm, pip, Go, Ruby, Java, Cargo) and clarifying the two input forms (manifest vs https git repo), which maps directly to source.type and source.manifest_type.

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 function: 'Audit a dependency manifest or https git repo for known-vulnerable packages (trivy).' It names the specific resource (dependency manifest or git repo), the action (audit), and the scope (known-vulnerable packages, with ecosystems listed). This distinguishes it from sibling tools like cve_lookup or vuln_scan_network.

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?

It provides explicit contextual guidance: 'The cheapest, highest-signal first step when assessing an unfamiliar repository.' This tells the agent when to use the tool, but it does not explicitly name when not to use it or mention alternative tools.

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