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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explains the severity levels: 'critical (past EOL — no security patches), warning (past active support), and ok,' giving insight into what the output means. It also notes 'Operated by an autonomous AI agent (Krab Bot); the free tier is used here,' adding operational context. However, it does not explicitly state whether the tool makes external API calls, whether results are cached, or potential rate limits. Still, the provided details go beyond minimal expectations.

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 four sentences long and front-loads the core purpose in the first sentence, followed by usage example, return semantics, and usage context. It is efficient, but the final sentence about Krab Bot and the free tier is somewhat tangential and could be removed without losing essential functionality. Otherwise, no dead weight.

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 single-parameter tool with no output schema and no annotations, the description covers the essential aspects: input format (with example), output categories, usage scenarios, and operational context. It lacks explicit details on error handling (e.g., invalid product format or exceeding 25 components), but these are minor for a straightforward check tool. The inclusion of return semantics partially compensates for the absence of an output 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?

The schema already describes the 'stack' parameter as 'Comma-separated components, each optionally product@version (max 25)' with 100% coverage. The description adds a concrete example ('node@16,python@3.8,postgresql@17'), which is helpful but does not introduce new semantics beyond the schema. With full schema coverage, the baseline is 3, and the example provides a small incremental benefit rather than a major enhancement.

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 purpose: 'Check whether components of a software stack are end-of-life, past active support, or affected by CVEs on CISA's Known Exploited Vulnerabilities catalog.' It uses a specific verb ('check'), identifies the resource ('software stack'), and defines the exact scope (EOL, active support, KEV CVEs). It also provides example input and output categories, effectively distinguishing it from sibling tools like check_package_risk, which likely focuses on individual packages.

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 gives explicit when-to-use guidance: 'Use before recommending or upgrading a runtime, or to audit a Dockerfile or CI config.' It tells users the appropriate automation contexts but does not explicitly mention when not to use it or compare with alternatives. Sibling tools (check_package_risk, find_open_source_bounties) are not referenced, so exclusions are absent. This places it between a clear context (4) and full when/when-not/alternatives guidance (5).

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