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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorld=false), and the description adds genuinely non-redundant behavior: dry-run by default, write only with apply:true, a snapshot kept for stages_undo, and a planHash guard that refuses the write if the plan drifted. It also flags that existing group-name clashes are resolved by policy. The one gap is that it doesn't say what 'overwrite'/'merge' actually do to pre-existing groups, which is the riskiest part of the operation.

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-loaded with the purpose, then a usage example, then the preview/apply caveat — a sensible order with no filler. The middle sentence is long and clause-heavy (scope + six rule kinds + naming + policy in one breath), which costs a bit of readability.

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 an 8-parameter, nested-object, write-capable tool with no output schema, the description covers the critical unknowns: that it is a dry run by default, what unlocks the write, the undo path, and the plan-hash safeguard. It does not describe what the preview returns (group list? counts? the planHash itself?), which is the main remaining hole given there is no output schema.

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 88%, so the baseline is 3 and the schema carries most of the load. The description still adds value with a fully worked rules example ({kind:'slice', axis:'X', mode:'count', count:8, cuts:[]}) and the naming template ({template:'Seg_{SLICE}'}), which shows how the nested objects compose in practice rather than just listing them.

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?

Opens with a specific verb+resource ('Creates structure groups with the Construction Stage Wizard plugin's group builder') and then enumerates the actual mechanics: scope selection, splitting rules, templated naming, clash policy. An agent knows exactly what the tool does. It does not, however, distinguish itself from the sibling auto_structure_groups, so it stops short of a 5.

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 a concrete use case ('segments of a deck for staged construction') with a literal rules/naming payload, so the agent can pattern-match a request to this tool. The preview/apply gating is stated clearly. What is missing is explicit when-not guidance — nothing says when to reach for auto_structure_groups or construction_stages instead.

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