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

Beyond the annotations, the description discloses important side effects and constraints: a report that changes nothing counts as a failure after 2 minutes, move avoids picking the old host again, withdraw ends a supervise round, and reviews/merges are moved. With output schema coverage present, the remaining gap around return values is acceptable, though broader auth or rate-limit behavior is not described.

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 purpose is front-loaded, followed by a structured action-by-action list that is dense but appropriate for a multi-action dispatcher. Some phrasing is telegraphic and compressed, but each action entry contributes operational information rather than repeating schema fields.

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 complex eight-parameter action-dispatch tool, the description covers all actions, relevant parameters, permission requirements, and notable side effects. An output schema exists, so it does not need to explain return values, and nothing critical for correct invocation appears missing.

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%, so the description carries the full burden and mostly succeeds: it maps task_key, step, open_only, placement_id, outcome, note, host_id, and action to their action-specific meanings and gives enum values for step and outcome. It does not define formats or constraints for identifiers such as placement_id or task_key, leaving some semantic detail implicit.

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 the tool's domain and enumerates each action (agenda, placements, placement, report, move, withdraw, schedule_now, hosts, doctor), making the resource and operations specific. It distinguishes hosts from list_hosts and notes which actions are privileged, though it does not broadly contrast Loop with other task-management siblings such as list_tasks or update_task.

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 clear context for each action and some conditions, such as when needs_you applies, how open_only filters placements, what happens when move is called without host_id, and the 2-minute failure rule for report. It also states permission boundaries for agenda, move, and withdraw, but lacks explicit when-not guidance or alternative routing beyond hosts being the same as list_hosts.

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