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

Goes well beyond the annotations by disclosing that thresholds are uncalibrated defaults, that output is a statistical signal and never a determination, that scoring is whole-series retrospective, and the full cost/payment mechanism ($0.01 USDC on Solana via x402, retry at _meta["x402/payment"]). No claim conflicts with readOnlyHint=false / destructiveHint=false; the absence of any mutation behavior is consistent with a paid compute call.

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-loads purpose and returned fields before caveats, then payment mechanics, so the agent gets the essentials first. Dense but almost every clause carries information; the HTTP-equivalent URL and payment retry instructions add length that a caller may need but that dilutes the core statement.

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?

With no output schema, the description compensates by naming the exact return constituents (per-point robust score, boolean flag, fired signals). It also covers cost, payment retry, preflight, and interpretation caveats, so an agent has everything needed to call it and interpret the result without guessing.

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%, so the baseline is 3; the description adds real meaning by warning that sensitivity presets are uncalibrated defaults and by framing the point-count range as a hard validity constraint. It does not elaborate on the relaxed/strict direction beyond what the enum description already states, so it edges above baseline rather than fully owning parameter semantics.

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 ('Anomaly detection for one numeric time series') with explicit bounds (8..10,000 points) and enumerates what it returns (per-point robust score, boolean flag, fired signals). The 'one numeric time series' scope implicitly separates it from the sibling anomaly_batch, and the named methods (median/MAD robust z, iqr_fence, step_change) make the operation 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?

Gives clear operating context: global whole-series retrospective statistics, free shape/size-only preflight before paying, and the exact x402 payment retry flow. It does not explicitly say when to prefer this over anomaly_batch or when a series is too short/streaming-inappropriate, so it stops short of full alternatives guidance.

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