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

Annotations already flag destructiveHint=true and readOnly=false, but the description adds substantial behaviour the agent could not infer: composite sections and load combinations are preserved and restored, groups are validated first, a snapshot is kept for stages_undo, and the write is refused if the plan hash differs. That is exactly the extra context a destructive tool needs.

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?

One dense paragraph that front-loads what is built and how it is written, with mode and preview/apply behaviour near the end. It is information-rich rather than padded, though the long parenthetical about composite sections makes the first sentence heavy and slightly harder to scan.

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 14-parameter tool with nested objects and no output schema, the description covers structure ordering, temporary groups, final stage, modes, validation, preview and undo. Remaining gaps are minor: it never says what the preview returns (notably the planHash needed for confirmPlanHash) and saveResult is left entirely to the 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 coverage is 79%, so the baseline is 3, but the description goes further by explaining sequencing semantics: groupsPerStage at a time, boundary/load groups riding in the first new stage, temporary groups toggled on and off with their stage, and an optional closing final stage. It does not explain saveResult or how naming/start interacts in replace mode, leaving some gaps.

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 names a specific verb and resource ('Builds a construction stage sequence') and identifies the exact machinery used (the Construction Stage Wizard plugin's bulk generator plus its stage planner). It also implicitly distinguishes itself from siblings such as stage_groups and cs_stage_summary by scoping the tool to sequence creation and write.

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 operating conditions: mode 'append' vs 'replace', preview-by-default unless apply: true, and validation before any write. What it lacks is an explicit pointer for when to choose a sibling instead, e.g. when to reach for stage_groups or cs_stage_report rather than this generator.

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