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

Beyond the annotations (which only say non-read-only, non-destructive, not idempotent), the description discloses that changes land directly while cancellation triggers an owner confirmation, and that a bulk create yields one receipt and one card. It omits the required idempotency_key contract, which matters for a non-idempotent mutation, and does not explain the confirmation_id/confirmation_via flow.

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 mode decision is front-loaded and the remaining sentences group statuses, dates, and priority into tight, scannable blocks with no filler. It is telegraphic in places (e.g. 'one call, one receipt, one card') but every clause carries information.

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 mutation tool with a complex anyOf body, 5 parameters, and no output schema, the description covers the main paths and key semantics but leaves the required idempotency_key, the confirmation flow, and the 25-task bulk limit undocumented. An agent could invoke it correctly for common cases but would stumble on retry safety and large batches.

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 description coverage is only 20%, so the description has to carry weight; it does well on the create/update/move branching, the tasks array, direction values, and the start_date/end_date vs due_date distinction. However it never mentions idempotency_key, confirmation_id, confirmation_via, project_id, kind, or source, and its status list (todo, in-progress, blocked, review, done, cancelled) omits backlog and planned, which the schema enum allows — a partial mismatch that could mislead.

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 and explicitly separates the three modes: create (no task_id), update (with task_id), and move (task_id + direction). An agent can tell exactly what the tool does and which branch of its own body schema to take without guessing.

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 gives clear conditional guidance — omit task_id to create, supply task_id to update, add direction to move — and notes that bulk creation happens through body.tasks in a single call. It does not reference siblings such as list_tasks or search for discovery, so it falls short of a full when-to-use/when-not narrative.

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