TODO を追加

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

With no annotations, the description carries the full burden and does so well: it discloses the default due behavior (next day at Account.defaultTime, default 09:00), timezone semantics, default repeat values, and a failure condition (trial/subscription expired → isError + code=PAYMENT_REQUIRED). It stops short of stating authentication requirements (implied by sign_in) or any rate limits, so it is not exhaustive.

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 is front-loaded and no sentence is pure filler, but the definition is a single long run-on paragraph mixing due defaults, repeat vocabulary, and payment failure. Bullets or short sections would improve scanability for an agent parsing it, though the information density is justified by the nested repeat schema.

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?

For a 5-parameter tool with a nested repeat object and no output schema, the description covers the tricky invocation aspects (due defaults, recurrence encoding, payment-required error). It omits auth prerequisites and says nothing about the response, but with no output schema defined the latter is less critical. Adequate for correct invocation given the schema's own descriptions.

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 60%, and the description compensates heavily for the complex parameters: it explains due formats and the date-only default-time behavior, and translates natural-language recurrence phrases into repeat object shapes (毎週 月水 → weekdays [2,4], 隔週 → interval 2, etc.). It says nothing about notes or sound, which remain schema-documented only, but adds real meaning beyond the schema for the high-complexity fields.

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+resource (「TODO を追加する」) and adds the creation source (source=mcp). It is trivially distinguishable from siblings like update_todo, complete_todo, snooze_todo, and delete_todo, which all operate on existing TODOs. No ambiguity about what the tool does.

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?

Rich guidance on optional parameters: pass only title for a bare TODO; pass due only when the user states a time (「明日 9 時」「今日 15 時」); pass YYYY-MM-DD for date-only; how to express recurrence. It does not, however, route among sibling tools or state exclusions (e.g., when to use update_todo instead), so it falls short of explicit alternative-selection guidance.

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