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

Annotations only declare the safety profile (readOnly=false, destructive=true, idempotent=true, openWorld=false); the description adds genuinely new behavioral context: it requires the project.edit permission, the resulting order is shared with everyone on the project, missing sibling ids in the FULL shape are refused rather than partially applied, and the RELATIVE shape's order is computed server-side. These are auth, blast-radius and error-semantics details the structured fields do not carry.

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?

Purpose is front-loaded in the first clause, and most of the length is load-bearing (permissions, refusal rule, sibling constraint, return value). It is still a single dense run-on paragraph of parentheticals; breaking the two input shapes into clearly separated sentences or bullets would improve scannability without losing content.

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 6 parameters, 0 required, no output schema and no nested objects, the description covers everything an agent needs: both invocation shapes, the constraint that the operation never reparents, the permission prerequisite, the shared-visibility side effect, and the fact that the resulting group order is returned. Nothing material is left to inference.

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 100%, so the baseline is 3, but the description adds interaction semantics the schema does not: it defines the two mutually exclusive input shapes, explains that null/omitted parentId means top-level tasks, and adds the constraint that the reference task must share the moved task's parent. It stops short of stating the exact required-parameter combinations per shape, which a zero-required-param schema would benefit from.

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 precise verb+resource+scope: 'Changes the manual order of tasks within one sibling group - the order the List and the Gantt display.' It explicitly separates itself from sibling mutations, noting that changing a task's parent 'is update_task's parentId field,' so an agent can distinguish reorder_tasks from update_task, move_task_to_epic and move_task_to_sprint without opening schemas.

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?

Gives clear when-to-use guidance for its two modes (complete sibling group vs. single-task relative move) and names update_task as the alternative for reparenting. It does not, however, contrast itself against other ordering-affecting siblings such as gantt_optimize, resource_leveler_analyze or auto_schedule_proposal, so the exclusion set against the wider tool list is incomplete.

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