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

The annotations already declare the operation read-only, idempotent, and non-destructive, so the bar is lower. The description adds useful context beyond annotations: no API key required, a 0.01 USDC/query price point, a 20-query session limit, and explicit 'no payment' for the preview. However, the cost and free statements sit side-by-side confusingly ('Price 0.01 USDC/query' followed by 'FREE preview'), and there is no disclosure of what the response contains or what happens at the query limit. This adds some value but also introduces ambiguity.

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 a multi-line promotional paragraph rather than a focused tool definition. It repeats the same idea multiple times ('No API key needed', 'FREE preview — no key, no payment', 'Try one of the sample questions now') and includes emojis and pricing details that could be summarized in one or two sentences. The essential functional information is buried within marketing copy.

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?

There is no output schema, and the description does not explain what the preview returns, how results are formatted, or how the question is used beyond being 'echoed back' (which is only in the schema). For a tool with only two optional parameters the description is partially sufficient, but it lacks any mention of return shape, error conditions, or behavior at session limits. The promotional tone fills space with incentives rather than completing the operational picture.

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 100%, with both slug and question clearly documented in the input schema. The description contributes sample questions that illustrate the potential content of the 'question' parameter, but it does not add any new meaning about how the parameters interact or their expected formats beyond what the schema already provides. Baseline 3 is appropriate.

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 identifies the resource (CISA Known Exploited Vulnerabilities kevwatch) and frames this as a 'FREE preview', so an agent can infer it provides free query access to that listing. However, it leans on promotional language ('call this now', 'Try one of the sample questions now') and never states the core function directly, such as 'returns public metadata for a listing' or 'answers a question against the CISA KEV dataset'. It also does not distinguish itself from sibling tools like data_session_query beyond being free.

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 repeatedly emphasizes 'no API key needed' and 'no payment', which implies this tool should be used for free exploration, but it never explicitly says when to use this tool instead of a paid alternative (e.g., data_session_query or data_session_open). There is no mention of when not to use it, no comparison to siblings, and no guidance about what the preview is meant to replace or complement. The 'max 20 queries/session' limit is stated but not tied to a usage decision.

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