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

The description goes beyond the annotations by revealing important side effects: for escrow Draft tasks, it automatically reserves and locks funds from the wallet and requires sufficient balance; for direct-settlement Draft, it explicitly states no funding happens. It also mentions the requirement for authentication and the follow-up event, providing a complete picture of the operation's behavior without contradicting any annotation flags.

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 lengthy but well-structured, starting with a clear one-sentence summary and then branching into mode-specific details. Each sentence carries essential information without redundancy, and the logical flow (status requirements -> per-mode behavior -> post-publish follow-up) makes it easy to parse. The front-loaded purpose sentence ensures quick comprehension.

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?

The description is quite complete for a complex mutation tool, covering preconditions, side effects, and next steps. Given the absence of an output schema, the description adequately explains what happens, though it doesn't explicitly address idempotency (calling publish on an already-published task) or the exact status transition naming. The annotations already cover idempotency, so this is a minor gap. Overall, it provides sufficient context to use the tool 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?

The input schema already provides high coverage (100%) for both apiKey and taskId, so the baseline is 3. The description adds meaning beyond the schema by stating that taskId must reference a task in Draft or Funded status, and that apiKey must be authenticated. This gives the agent a better understanding of the valid parameter values and preconditions, though it doesn't elaborate on error formats or return types.

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 opens with a specific verb+resource: 'Publish a task to make it visible to operators.' It clearly distinguishes the tool from sibling tools like fund_task or request_task_quote by detailing that it works for both escrow and direct settlement modes, and the different states (Draft vs. Funded) where it applies. The title 'Publish Task' is expanded with concrete outcome and mode-specific behavior, leaving no ambiguity about its function.

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 explicitly states when to use the tool: the task must be in Draft or Funded status, and it works for both settlement modes. It also explains the direct-settlement shortcut versus the escrow flow, contrasting with fund_task and other related operations. It provides clear next steps ('wait for task.accepted via get_task_events or webhook'), giving the agent actionable guidance on post-publish workflow.

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