calculate_risk_score

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds significant behavioral context beyond these: the detailed formula, multiplicative boosters, clamping, label bands, urgency encoding, and output structure. No contradictions with annotations.

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 comprehensive and well-structured, starting with the core purpose, formula, and usage guidance. It includes necessary details like output fields and rate limits. However, it is slightly lengthy and includes secondary information (attribution, rate limits) that could be omitted or placed elsewhere without losing essential meaning.

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 and an output schema, the description fully explains the return values (fields like cve_id, score, label, etc.) and the tool's behavior. It also covers the context of sibling tools and provides sufficient detail for an AI agent to understand and invoke the tool correctly.

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% with a single required parameter. The description adds concrete meaning by specifying the format and examples for cve_id (e.g., CVE-2021-44228). This goes beyond the schema's description, which also mentions the format.

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 that the tool computes a composite risk score for a CVE by fusing CVSS, EPSS, KEV, and PoC. It specifies the formula, label bands, and urgency, and distinguishes itself from sibling tools like cve_lookup and exploit_lookup by highlighting that it avoids orchestrating multiple lookups.

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 explicitly tells when to use the tool ('triage a single CVE without orchestrating cve_lookup + exploit_lookup separately') and when not to use it ('for full multi-source exploit detail, call exploit_lookup separately'). It also provides alternatives, fulfilling the dimension perfectly.

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