folder_stats

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

Annotations already indicate readOnly and idempotent, but description adds significant behavioral context: partial result detection (scanned/truncated), exactness of total/unread counts, cap on aggregations, and rejection of non-selectable containers with actionable errors.

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?

Front-loaded with purpose, then parameter behavior, then edge case. Two key sentences plus a third for error handling. No wasted words; every sentence earns its place.

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 low complexity (2 simple params, no output schema), description is thorough: covers purpose, parameter details, behavioral traits (truncation detection, exact counts), and error handling. No gaps for safe agent invocation.

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 covers both parameters (100% coverage), but description adds valuable nuance: for scanLimit, clarifies that total/unread counts are always exact while aggregations are capped, and that response includes scanned/truncated; for folder, restates default. Adds meaning beyond 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?

Description clearly states 'Return aggregate stats for a folder' with specific details about total/unread counts and scanned-envelope aggregations (oldest/newest/total bytes), distinguishing it from sibling tools like count_messages or list_folders.

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?

Provides clear context on scanLimit defaults and max, explains how to detect partial results via scanned/truncated response fields, and mentions error handling for non-selectable containers, but does not explicitly state when to use this tool versus alternatives.

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