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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds a genuinely non-obvious behavioral contract: this tool never raises a protocol error, it returns an {"error": ...} object, and retry after correction is always safe. That is exactly the kind of information annotations cannot convey.

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?

Purpose, cost, example, and routing guidance are front-loaded and easy to scan. The closing error paragraph is slightly wordy (the retry-safety point could be one clause), but every sentence carries usable information.

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?

Output schema exists and annotations cover safety, so the description only needs to add ordering semantics, sibling routing, and failure behavior — all present. Nothing an agent needs to invoke this 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?

Schema coverage is 100% and the single parameter already documents 'oldest first, at least 2 values' with the same example the description uses. The description's example input/output pair helps confirm ordering semantics but largely restates structured data, so baseline 3 applies.

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?

States a specific verb and resource ('Compute period-over-period growth and CAGR') and names the exact input shape it operates on. It also explicitly distinguishes itself from the two nearest siblings, ab_test and forecast_trend, so an agent can route without opening schemas.

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?

Gives an explicit positive condition ('when one series is already in period order') and two explicit exclusions with named alternatives ('not for comparing two variants (ab_test)', 'not for projecting (forecast_trend)'). This is textbook when/when-not/alternatives coverage.

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