Change dimensions and tags

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

Annotations flag a destructive, non-read-only edit, and the description goes well beyond that: it explains that anchor makes dimensions re-measure on every change, what happens to already-off dimensions ('comes back in left [[id, written, measured, near]]'), what happens when an anchor's piece is deleted, and that bake permanently converts automatic chains into editable dimensions. These are meaningful behavioral consequences the annotations 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?

The body is one dense run-on block of poorly punctuated prose with embedded return-shape literals ('{dims,refs,details,legend,rooms:[[room,[[tag,...]]]]}') that is hard to parse and not front-loaded. Several clauses duplicate the per-parameter schema descriptions verbatim, so the text is not earning its length.

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?

The tool is complex (7 modes, mutation, output schema), and the description covers the destructive switches, the anchor lifecycle, and what the mode responses contain. With an output schema and annotations already present, the remaining gaps (no explicit when-to-use routing) are minor; completeness is largely satisfied.

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 schema already documents all seven flags and the description largely restates them. It does add some nuance (renumber's reading-order behavior, the shape refs=true returns, legend/chains output formats), but much of this overlaps with the per-parameter schema text rather than extending it, so the baseline of 3 is appropriate.

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 verb+resource is clear ('Change the plan annotations') and the description enumerates the concrete facets it operates on: dims, refs, details, legend, bake, anchor. It also implicitly distinguishes itself from the read-only sibling with '`annotations` reads them.' It stops short of a crisp one-line scope statement, but an agent can tell what it does.

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?

There is real conditional guidance for one mode ('tie them while the numbers are right' / 'Run it while the numbers are right'), and the pointer that `annotations` reads rather than edits. But for the other six switches (dims, refs, legend, details, renumber, bake) there is no when-to-use, sequencing, or alternative-selection guidance — usage is implied by the mode descriptions rather than stated.

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