detect_follow_through_day

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

Annotations already declare readOnly, idempotent, non-destructive. The description adds meaningful context: it is cache-only with no API call, and data arrives ~17:15 JST. This enriches behavioral understanding beyond the structured hints, though it doesn't discuss failure modes or edge cases like missing data.

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 somewhat long but well-structured: purpose, use case, data availability, supported plans, and args. Every section serves a purpose, though the 'All plans' line is redundant with the subsequent '[Supported plans]' line. Still, it's efficiently organized and easy to parse.

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?

The tool is moderately complex, but the description covers the detection logic, parameter formats, defaults, data timing, and plan restrictions. An output schema exists, so return values need no explanation. This description is complete enough for an agent to select and invoke the tool correctly.

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 0%, so the description carries full responsibility for explaining parameters. It does so thoroughly: rally_start is described as 'the low/reversal day' with accepted formats, date defaults to latest cached, and sigma_multiplier threshold with default 2.0. This fully compensates for the empty schema descriptions.

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 states the tool's function: 'Check whether a follow-through day confirms a new uptrend.' It specifies the IBD method and the exact condition (TOPIX z-score ≥ +sigma on session 4+ from rally_start). This distinguishes it from sibling tools, and it even references detect_distribution_days as a related alternative.

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?

Explicitly states when to use: 'Use when asking if a rally attempt is confirmed (IBD method).' It provides concrete criteria (session 4+, higher market turnover) and points to an alternative tool. It also notes the data availability time, which helps set expectations for usage.

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