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

Annotations (readOnlyHint, idempotentHint, etc.) are already present, and the description adds useful context: 'data refreshed on each call, 1-hour cache', rate limit, and no auth. No contradictions.

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?

Description is about 5 sentences, front-loaded with purpose and key details. The fallback instruction is appended but not excessive. Good balance of information.

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?

Lists return fields (e.g., anomaly_score range, maintainer_health enum), data sources, caching, rate limits, and auth. For a tool with output schema, this provides sufficient context beyond the schema.

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%, but the description mentions only 'npm or PyPI' while the schema includes 'cargo' and 'go', potentially causing confusion. Baseline 3 is appropriate for a schema that covers parameters, but the mismatch reduces clarity.

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 action ('Analyse ownership and release history') and the goal ('detect supply-chain risk') for npm or PyPI packages, distinguishing it from sibling tools like security_fetch_package_risk_brief.

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?

Explicitly targets security engineers auditing dependencies for production builds, and includes fallback guidance (report_feedback) for non-serving responses. Lacks explicit when-not-to-use but context is clear.

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