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

With no annotations present, the description carries the full burden and does well: it declares read-only status and, unusually, documents the permission/visibility model (a field worker sees only their own follow-ups; the owner and office see the whole shop's). It also states that each row contains the words and the op to call, so the agent knows the output is actionable rather than passive.

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?

Three short sentences with no filler, and the core purpose is front-loaded ahead of the visibility caveat. The parenthetical '(tasks.create with for_agent)' earns its place by explaining provenance, though it is slightly cryptic without that tool's context.

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 one-parameter read tool with an existing output schema, the description covers the essentials: what is returned, what it is scoped to, who sees what, and that it is safe. The one real gap is the unexplained required shop_id argument.

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 0% for the single required shop_id parameter, and the description never mentions it. The phrase 'the shop's' hints at shop scoping but does not explain the parameter, its UUID format, or how it interacts with the visibility rule described.

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 gives a specific verb-and-resource: it returns follow-ups the agent scheduled for itself that are due now, and it anchors the concept by naming the originating call (tasks.create with for_agent). This cleanly separates it from the human-facing services_listDue family, though it never explicitly contrasts with the other agent_* siblings.

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?

Usage is implied by the 'due now' scoping and the statement that each row carries the op to call, so an agent can infer this is the polling entry point for self-scheduled work. There is no explicit when-not guidance or direction to agent_checkup / agent_snooze for other agent state.

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