Move a note section

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

Annotations only declare the basic safety profile (not read-only, destructive, non-idempotent, closed-world). The description adds considerable context beyond that: dry-run vs commit semantics, durable history and index reconciliation on commit, byte-level preservation including frontmatter, refusal of mixed EOLs/unsafe boundaries/invalid child hierarchy, and the request_id replay mechanism. This is exactly the behavioral detail annotations cannot 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 and mode switch are front-loaded, and each sentence carries distinct operational information (mode, preconditions, refusals, selectors, disambiguation). It is dense and long, but for a destructive 10-parameter tool almost every clause earns its place; only minor tightening is possible.

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 need not be restated, yet the description still tells the agent what the dry-run returns (selection coordinates, before/projected hashes). Combined with precondition handling, refusal cases, and duplicate-heading disambiguation, it gives an agent everything needed to invoke this complex mutation correctly.

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% across 10 parameters, so the description must compensate, and it does for most: confirm (default false preview vs true commit), expected_hash (required), request_id (stable, for durable replay receipts), and the level/occurrence pairs (duplicate titles require the respective level and 1-based occurrence). rel_path is left self-evident and the level/occurrence tie-in could be stated more directly, so not quite a 5.

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 specific verb+resource and scope: an exact single-note H2-H6 subtree move to an existing heading's final child position. The scope qualifiers (single-note, no releveling, H2-H6) let an agent distinguish this from rename_note_section, delete_note_section, and patch_note_section 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?

Opens with 'Use this to preview...' and clearly separates the two modes (confirm=false returns coordinates/hashes without writing; confirm=true commits). Preconditions are explicit (both headings must exist, expected_hash required, no releveling). It does not explicitly name sibling alternatives to route against, so it stops short of 5.

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