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

Annotations already mark destructiveHint=true, but the description adds valuable behavioral context: it spends money, creates a real-world action, requires user confirmation, and describes payment/refund conditions (completed tasks pay worker; failed/expired/pre-acceptance cancelled refund escrow). This goes beyond what annotations provide.

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 four sentences and each conveys necessary information: action/use cases, mandatory quote step, execution/evidence, and financial outcomes. It is slightly dense but front-loaded and without fluff.

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?

Given the tool's complexity (12 parameters, 9 required, no output schema), the description covers the critical workflow and financial consequences. It does not detail all parameter requirements, but the schema covers many, and the description adequately explains the tool's real-world impact.

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 58%, so the description carries some weight. It adds general context for reward 'spends money' and location 'nearby real human/physical location', but does not explain specific parameter semantics like task_type options, reward bounds, or expiry defaults, leaving gaps that the schema only partially fills.

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 identifies the action: 'Send a nearby real human to a physical location' and enumerates use cases (verification, checks, photos, queue, pickup). It distinguishes from siblings by explicitly requiring errand_quote first, which differentiates it from quote/cancel/status 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?

It gives explicit prerequisites: call errand_quote first, present its exact total_charge_krw, and obtain explicit user confirmation. However, it does not explicitly state when not to use the tool or name alternative tools for status/result retrieval, so it falls short of a 5.

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