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

Despite destructiveHint=true annotation being present, the description adds substantial behavioral detail: it explicitly lists what discard deletes (the row, marks, actual times, reflection-added events), what confirm freezes (adherence snapshot, dayReviews row), that re-confirming refreshes, and that it's reversible via undoToken within 30 minutes. This far exceeds what annotations alone convey.

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 a single dense paragraph, well-organized with comma-separated clarifications. Every sentence adds functional information (what confirm does, what discard does, constraints, reversibility). It's appropriately sized for a tool with two distinct actions each having complex effects, though the long first sentence could be tighter.

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 two-parameter tool with destructive annotatons and no output schema, the description is very complete: it covers both actions' full effects, prerequisites (write_events reflect op), constraints (past day, must be within plan range), side effects on get_schedule and stats, and reversibility via undoToken. Nothing critical is missing for an agent to invoke 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 50%: the action param has a description in the schema, but date has none. The description explains date is ISO YYYY-MM-DD and only past days, and explains the action enum values in depth ('confirm freezes adherence snapshot', 'discard resets'). This adds value beyond schema for action but only mildly for date. Baseline 3 is fair.

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 a specific verb+resource: 'Confirm or discard a whole PAST day's reflection (by `date`...)'. It distinguishes from siblings by noting it works on a whole day's reflection, uses the date param, and is different from write_events which marks individual events. The two actions (confirm/discard) are clearly explained.

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?

The description gives clear context on when to use it: after marking events with write_events' reflect op. It states constraints (only past days, days too far back rejected). However it doesn't explicitly name alternatives or say when NOT to use it, though it references write_events as the prerequisite marking step, implying differentiation.

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