detect_ytd_high_low_range

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses caching behavior ('cache-only, no API call'), data availability time, and the cache-bypass effect when 'code' is set. These are significant behavioral traits that the annotations do not cover.

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 structure is clear with sections for purpose, usage, plans, and arguments, and it is front-loaded. However, the 'date_from within 52 weeks' constraint appears twice (in the intro and in the Args), creating minor redundancy, and the reference to another tool for min_prior_sessions is a slight detour.

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 description covers purpose, alternatives, constraints, parameter semantics, caching, and availability. The only gap is the reliance on detect_ytd_high_low for min_prior_sessions, but the output schema likely handles return structure, so the core contextual needs are satisfied.

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?

With 0% schema coverage, the description fully compensates by documenting all five parameters: formats, inclusive ranges, defaults, and the special effect of 'code'. The Args section turns an otherwise opaque schema into a usable reference.

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 opens with a specific verb ('Scan') and resource ('year-to-date high/low records') scoped to a date range, which clearly distinguishes it from the sibling detect_ytd_high_low (single date) and detect_52w_high_low_range (52-week range). The Japanese annotation further clarifies the concept.

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?

It explicitly advises using this tool instead of repeated detect_ytd_high_low calls for multi-day queries and warns against splitting into parallel range calls. It also provides concrete constraints (date_from within past 52 weeks) and data availability timing (~17:15 JST), which are directly actionable.

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