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

The description clearly states the tool is 'read-only and idempotent' and reveals a crucial behavioral trait: instead of throwing protocol errors, it returns a structured error object with a fix message. The annotations already declare `readOnlyHint: true`, `idempotentHint: true`, and `destructiveHint: false`, so the bar for transparency is lower. The description goes beyond annotations by detailing the error-handling behavior and retry safety. No contradictions with annotations are present.

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, front-loading the core purpose in the opening sentence. Every sentence contributes distinct value: purpose, example input/output, usage guidance, error handling, and idempotency assurance. No filler or repetition. It is highly efficient and earns every word.

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 low complexity (single required parameter), the presence of a clear output schema, and rich annotations, the description is nearly complete. It provides an illustrative example, usage guidelines, sibling differentiation, and error behavior. The only slight gap is that it does not explicitly state the return type format (e.g., that it returns an object with specific keys) beyond the JSON example, but the output schema covers this. For a one-parameter tool, this is very complete.

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 input schema has perfect coverage (100%), with a detailed description for the `values` parameter ('Ordered numeric series, oldest first, at least 2 values'). The tool's description reinforces this with a concrete example. Since schema coverage is complete, the baseline is 3. The description adds an example but does not significantly expand on the semantics already present in 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 specifies the action ('Compute period-over-period growth and CAGR'), the target resource ('numeric series'), and the output format with an example. It distinguishes the tool from siblings by naming `ab_test` and `forecast_trend` and stating what it does not do ('Not for comparing two variants' and 'not for projecting future periods'), making the purpose highly specific and unambiguous.

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 explicitly states when to use this tool ('Use when one series is already in period order') and explicitly when not to use it, naming two sibling alternatives (`ab_test` and `forecast_trend`) with different purposes. This provides clear context for selection and exclusion, meeting the highest standard for usage guidance.

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