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

Annotations give only basic hints (not read-only, not idempotent, not destructive). The description adds substantial behavioral context: the human review means execution is not instant, the operator is push-notified on submission, contact_email is MX-checked and placeholder domains are rejected, and status_poll delivers results via operator_notes with a one-per-client-per-day limit. This exceeds the annotation burden meaningfully.

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 compact yet dense with useful information. It front-loads the most important behavioral caveat (not instant execution) and then flows naturally through tracking, pricing, and delivery options. Every sentence earns its place; there is no redundancy or filler.

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 tool with no output schema, the description is remarkably complete. It covers the submission lifecycle, the asynchronous review model, how the deliverable reaches the agent, fallback behavior for mailbox-less agents, and the rate limit. An agent has enough context to call the tool correctly and set expectations about the async result.

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 schema already covers all 9 parameters (100% coverage), but the description adds crucial semantic detail beyond the schema: it clarifies the relationship between delivery and contact_email (no mailbox means use status_poll), explains that a task_id is the only key for tracking the deliverable, and notes that location_detail is 'required in practice' when location_required is true. This is valuable guidance the schema alone does not provide.

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 ('submit') and resource ('a task for the human operator to perform in the real world'). It immediately differentiates from the sibling status-check tools by noting it returns a task_id immediately while the human reviews before accepting. This clearly distinguishes the submission action from check_task_status and other sibling tools.

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 tells the agent when to use this tool (submit a real-world task) and when to use the alternative (check_task_status to track progress). It also routes the agent to get_human_services for task_type category descriptions, and explains the delivery-mode alternatives for agents with or without a mailbox, including the status_poll budget constraint.

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