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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral details: it returns both millisecond values and human-readable durations, shows default configurations before customization, and notes the fixed 30-minute response cache duration. This goes beyond the annotations, though it includes a minor irrelevant note about auto-registration.

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 well-structured with sections, but it includes non-essential content like an 'Advantages' bullet list and a 'Related Tools' list that duplicate information available from siblings. While the core information is front-loaded, the verbosity could be trimmed without losing value. It's not as concise as the high-scoring examples.

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 optional parameter, no output schema), the description is complete. It explains the parameter, the return format, default behavior, and fixed characteristics. It also mentions related tools for further context. Nothing an agent needs to invoke it correctly is missing.

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 has 0% description coverage (no descriptions in the input schema properties), so the description must compensate. It does so thoroughly: 'cacheType (string): Which cache config to retrieve - "simulator", "project", "response", or "all". Defaults to "all"' — this documents the parameter's purpose, allowed values, and default, fully exceeding what the schema provides.

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: 'Retrieves the current cache retention policies for simulator, project, and response caches.' It uses a specific verb (retrieves) and resource (cache retention configuration). While it doesn't explicitly contrast with siblings, the purpose is unambiguous and easily distinguished from related tools like cache-set-config or cache-clear.

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 provides clear usage context: 'Essential for understanding your current cache configuration before making adjustments or troubleshooting performance' and 'Use to verify config changes after using cache-set-config.' It implies when to use the tool but doesn't explicitly state when not to use it or contrast with alternatives beyond listing related tools. This is slightly below the explicit guidance in the calibration example.

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