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

Beyond the readOnlyHint and idempotentHint annotations, the description reveals crucial behavioral details: per-user cursor stored in Redis, first-call window, subsequent incremental returns, no external API calls, and instant response. It also provides a feedback fallback if results are insufficient, adding transparency about limitations.

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 fairly detailed but well-organized, starting with the core purpose, then efficiency note, parameter explanation, behavioral details, source, and feedback instruction. Some repetition of the parameter description exists, but each sentence contributes useful information without excessive padding.

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 tool has an output schema, so return format is covered, and the description thoroughly addresses behavior, data source, performance characteristics, and error handling (feedback path). It is complete for a polling tool with stateful behavior, leaving no important aspect unexplored.

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% and the description reiterates the parameter's meaning, but crucially it adds that the IDs are the same as those used in security_fetch_cve_watch, providing essential context about where to obtain valid watch IDs. This adds value beyond the schema baseline.

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 verb (check) and resource (CVE watches) and specifies it returns only watches with new events, distinguishing it from sibling creation tool security_fetch_cve_watch. It is specific and unambiguous.

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?

It explicitly mentions running on a schedule and explains the behavior (first call returns last 30 days, subsequent calls only newer events), which guides when to use it. It does not mention alternatives explicitly but the linkage to security_fetch_cve_watch and the polling nature make context clear.

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