search_by_keyword

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

With no annotations, the description carries full burden. It discloses key behaviors: normalizes common variations, searches NVD, GitHub Advisory, and OSV concurrently, and deduplicates results. This provides good transparency for an AI agent, though some details like rate limits or result ordering are omitted.

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 with four sentences including examples. It front-loads the purpose and adds behavioral details without waste. Every sentence adds value.

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?

The description covers the main search behavior and data sources, which is adequate for a simple tool with an output schema. However, it fails to explain the 'limit' parameter, and could mention return formatting or pagination. It is minimally complete but has clear gaps.

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 0%, so the description must compensate. It provides example usage for the keyword parameter, but does not explain the 'limit' parameter (default 30) or its effect. Thus, only partial semantic coverage is achieved.

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 it searches for CVEs by technology/library keyword, with specific verbs and resource. It distinguishes itself from sibling tools like search_cve_by_id (by ID) and search_vulnerabilities_by_product (by product) by focusing on keyword normalization and multi-source search.

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 implies when to use the tool (for keyword-based CVE search) but does not explicitly state when not to use it or compare with alternatives. The sibling list is provided externally, but the description lacks direct guidance on choosing this tool over others.

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