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

The annotations already declare this is a non-readonly, non-destructive, non-idempotent write. Beyond that, the description discloses a real side effect (a board is auto-created on first use), a dedupe constraint (duplicate open tasks are refused, which explains the non-idempotent hint), and quota limits. It omits any mention of permissions or what happens when a quota is hit.

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?

Four short sentences, front-loaded with purpose and return values, with no filler. The final line "Free: 3 boards, 200 open." is telegraphic enough to be slightly ambiguous about what exactly is capped.

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?

With no output schema, the description helpfully names the returned fields (id, board, column), and the eight parameters are fully documented in the schema. Missing only edge-case behavior for quota exhaustion and what the refusal error looks like for a duplicate task.

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 100%, and the schema already explains defaults for project, column, and priority, so the baseline is 3. The description only restates the project-optional behavior and adds no new semantics such as partial-name matching rules or tag normalization.

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?

"Add one task to a board and return its id, board and column" gives a specific verb (add), resource (task), scope (one), and even the shape of the result. The verb alone separates it from siblings like task_update, task_move, and task_done, so an agent can route without opening the schema.

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 states key preconditions: the board is created on first use, an existing project can be passed or omitted, and an identical open task is refused. It does not explicitly name an alternative tool for editing an existing task (task_update) or searching before adding (task_search), so it falls short of full when/when-not guidance.

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