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

The description adds significant value beyond annotations: it explains the free tier, input format with example, output format with example, per-event error handling (doesn't fail whole call), error response format, and explicitly states read-only and idempotent behavior. Annotations already provided readOnlyHint=true and idempotentHint=true, but the description adds rich context about error handling and retry safety.

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 clear sections: purpose, example, usage notes, error behavior. It is reasonably concise but could be slightly tighter; the error handling explanation is a bit verbose. However, it front-loads the key info ('Count the days until each named event') and earns its sentences.

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 (1 parameter, 100% schema coverage, output schema present, annotations present), the description is complete. It covers purpose, input/output examples, error handling, usage boundaries, and safety guarantees. No gaps remain for an AI agent to correctly select and invoke this tool.

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 description provides a concrete example of the events parameter ('{"Launch": "2026-10-01", "Trip": "2026-09-05"}') and explains the limit ('The first 30 events are used'). Since schema coverage is 100% and the schema already describes the parameter, the description's example adds value by showing the exact format, though it doesn't elaborate on all edge cases (e.g., what happens with duplicate event names).

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 explicitly states 'Count the days until each named event, soonest first' with a specific verb ('Count') and resource ('days until named events'). It distinguishes itself from siblings by mentioning 'Not for working-day math' (business_days) and 'not for building a review schedule' (spaced_repetition_plan).

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 guidance: 'Use to rank named dates by how soon they arrive' and explicitly states when not to use it ('Not for working-day math... not for building a review schedule') with named alternatives (timeops server's business_days, spaced_repetition_plan). It also includes error handling instructions and retry safety.

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