session

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false and readOnlyHint=false. The description adds real value by explaining the transaction/rollback/redo model, which is not derivable from annotations. However, it does not distinguish which of the ten actions are safe reads (status, get_steps, list) from destructive ones (rollback discards steps, complete writes a file), which is exactly the context an agent needs given the blanket destructiveHint.

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?

Two compact blocks: a one-line conceptual framing followed by a dense action/parameter map. Front-loaded and free of filler, though the pipe-delimited action list is terse enough that some semantic detail is sacrificed for brevity.

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?

An output schema exists, so return values needn't be described. For a 10-action, 16-parameter dispatcher the description covers the call shape well but leaves per-action behavior undefined (what to_step=null means, whether pause persists state, what 'force' overrides), relying on operation_help to fill the gap.

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% — parameters carry only title/default metadata — so the description must compensate, and it does: it maps nearly every parameter to its action (start: doc_name/create_document, rollback: to_step/force, redo: n, add_note: note/note_type, resume: session_id, complete: save/save_path/description/tags, get_steps: limit/offset). Only 'name' and the optionality/format semantics of to_step are unaddressed.

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 opening sentence states a specific resource and its defining behavior: a modeling session bound to a document, with cad() mutations becoming transaction-backed, rollback-able steps. It distinguishes itself from the sibling assembly_session by being the modeling/CAD-edit session. It's clear, though the multi-action dispatcher nature means no single verb captures the tool.

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?

The action list implies what each mode does (start, rollback, redo, complete, etc.) but never says when to reach for this tool versus alternatives like step_plan, step_control, or assembly_session. There are no exclusions or prerequisites, and it deflects detail to operation_help("session").

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