TODO を完了

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

With no annotations present, the description carries the full burden and does well: it discloses the exact mutations for each case (status=done + completedAt for one-off; a done Occurrence record keyed by occurrenceDate for recurring). It omits idempotency, error states (e.g., already-completed), and auth requirements, keeping it short of a 5.

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 action ('やった、にする') is front-loaded, and the remaining clauses each earn their place by covering the two execution branches. It is dense but free of filler; slightly telegraphic phrasing is the only minor cost.

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 2-parameter mutation tool with no annotations and no output schema, the definition covers the important complexity: the divergence between one-off and recurring completion, plus the optional date semantics. Error/edge behavior and return expectations are the only meaningful gaps.

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 50%: occurrenceDate is documented, id is not. The description adds real value beyond the schema by specifying the timeZone-aware default ('today in the TODO's timeZone'), which the schema's terse '省略で今日' does not clarify. It adds nothing for the required id parameter, so a 3 is appropriate.

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 states a specific verb+resource ('mark as done') and goes further by splitting the behavior into one-off vs. recurring cases. It implicitly separates this from update_todo via completion semantics, but never names or contrasts a sibling explicitly, so it lands at 4 rather than 5.

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?

Usage is implied by the completion semantics and the single-vs-recurring branch, which tells an agent which code path applies. However, there is no guidance on when to prefer complete_todo over update_todo or snooze_todo, and no stated preconditions or exclusions.

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