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

Annotations only declare destructiveHint=true, so the description carries real weight and delivers: it declares the write operation, the return values (job_id and tracking link), and the forced ignore_customer_lat_long=1 behavior so the agent knows a stored address will not be used. It omits side effects such as notifications fan-out and whether duplicate submissions create duplicate jobs.

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?

Front-loads the verb and required inputs, then layers optional assignment and return behavior, all in a dense paragraph with no filler. The trailing endpoint/flag metadata ('POST /v2/create_task (has_pickup 0, has_delivery 1, layout_type 0)') is low-value for an agent and slightly clutters the close.

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 15 parameters, no output schema, and minimal annotations, the description covers the essentials: what is created, what is required, how assignment works, address precedence, and what is returned. Missing only duplicate-handling and notification side-effect notes, which are secondary for a create call.

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 coverage is 100%, so the baseline is 3; the description earns above that by explaining the interaction between fleet_id, team_id, and auto_assignment, and by clarifying that the address parameter overrides any saved customer location. Parameter-level detail for the remaining fields is left to the schema, which is appropriate.

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?

States a specific verb and resource ('create a delivery task (job) for a customer address') plus the scheduling constraint, immediately distinguishing it from every sibling, which are all read, list, assign, or status-update operations. An agent knows exactly what this tool produces.

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?

Explains the creation-time assignment options (fleet_id, team_id, or auto-assign within a team), which is genuine when-to-use guidance for the branching paths. It does not explicitly say when to prefer tookan_assign_agent_to_task afterwards or when not to use this tool, so it stops short of full alternative routing.

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