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

The description explicitly begins with 'Read-only,' which is a clear and important behavioral guarantee, especially since no annotations are present. It does not mention output format or error behavior, but the read-only nature is the key side-effect signal for an agent.

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 short, front-loaded with the purpose, and then provides metric-specific definitions and a docs pointer. Every sentence carries useful information, with no filler or 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?

For a one-parameter read-only scorecard, the description supplies enough context: purpose, metric definitions, data sources, and a reference to additional documentation. The presence of an output schema means the prose does not need to enumerate return fields, and the doc pointer covers deeper details.

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 'days' parameter is well-described in the schema: it defines the window and explicitly connects it to closed sessions, durable rows, and llm_usage records, with a default of 7. Since schema coverage is 100%, the description adds useful operational context rather than repeating the schema.

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 identifies this as a read-only scorecard for distiller effectiveness and enumerates the four specific metrics it reports: coverage, attribution, crumb rate, and cost. The title and description align, and the scope is distinct enough from other memory-report tools even without naming siblings.

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 what the tool measures and where each metric comes from, but it does not state when to call this tool versus other memory or reporting tools. No scenario guidance or explicit alternatives are provided.

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