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

Beyond annotations (readOnly, idempotent, etc.), the description details internal behavior: per-user cursor in Redis, first call returning 30 days, subsequent calls returning only new events, no external API calls, instant response. 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 efficiently structured, starting with the main purpose, then explaining efficiency, parameter, behavior, and sources. Every sentence adds value without redundancy.

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's simplicity (one parameter, output schema exists), the description thoroughly covers purpose, parameter semantics, behavior, cursor mechanism, sources, and even a fallback action. It leaves no significant 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?

The schema describes watch_ids with a basic example. The description adds crucial context: these are the same IDs used when creating watches with security_fetch_cve_watch. Since schema coverage is 100%, baseline is 3, but the extra linkage raises the score.

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 checks all specified CVE watches for new events since the last poll, uses a per-user cursor, and returns only watches with new events. It explicitly references the sibling tool security_fetch_cve_watch for creation, distinguishing their roles.

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 explains it is efficient for scheduling and specifies the relationship to the creation tool, implying when to use it. It also provides a fallback to report_feedback if results are insufficient. However, it does not explicitly mention when not to use it or list alternative tools beyond the implicit sibling.

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