task_run

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

With no annotations provided, the description carries the full burden and delivers richly: it discloses the historical misnomer, that values were previously silently dropped, that priority/horizon are honored now (fixed 2026-07-27), and that the tool only creates a row, never executes. This goes well beyond what annotations would have covered.

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 well-structured with three focused paragraphs: what it does, what it doesn't do, and why the name/behavior is the way it is. The history note is slightly verbose for a tool description but earns its place by preventing callers from assuming execution behavior. Slightly long but efficiently organized.

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 9-parameter task-creation tool with full schema coverage and an output schema, the description covers the critical gaps: it clarifies the no-execution behavior, dispatch responsibility, memo feedback loop, and priority/horizon semantics. It doesn't enumerate every parameter (schema does that), and the output schema presumably describes return values. Reasonably complete for its complexity.

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%, so the schema documents all 9 parameters. The description adds context that priority and horizon 'drive the task wall's ordering' — valuable behavioral framing beyond the schema's enum strings. However, it doesn't elaborate on tags, depends_on, assigned_to, or model semantics; baseline 3 is appropriate with full schema coverage.

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 the tool 'puts a task on a team's wall' and explicitly clarifies it does NOT execute tasks — distinct from what the historical name implies. It effectively distinguishes from task_create/task_update siblings by framing this as wall-posting with separate dispatch, though it doesn't name an alternative tool directly.

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 explicit guidance on when this tool is appropriate: it creates the wall row only, dispatch is left to the caller via Agent(...) / SendMessage, and progress is written back via task_memo_add. It explicitly warns that nothing executes the task and an Agent must pick it up, which is valuable exclusions guidance.

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