Change dimensions and tags

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

Despite destructiveHint=true being present, the description goes far beyond it: it discloses that anchor ties dimensions to current geometry and re-measures them on every change, that tags persist with a piece and leave gaps when removed, that dead anchors are re-tied or released, and that bake turns automatic chains into editable dimensions. This gives the agent a strong model of side effects and persistence.

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 description is a single dense, run-on block with nested clauses and parentheticals that are very hard to scan (for example, the anchor sentence and the long refs/legend sentence). While the content is relevant, it needs bulleted modes and clearer separation to be efficiently parseable by an agent.

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 multi-mode destructive tool with seven switches, the description covers the essentials: prerequisites for anchor, behavior on stale or deleted anchors, return shapes for modes, renumbering semantics, and the relationship to the annotations read tool. The output schema exists, so the detailed return-value prose is bonus rather than a required 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?

The schema already covers all seven boolean parameters, but the description adds real semantics: what each switch returns (e.g. chains [[from,to,cm]] for dims, symbols {discipline:[[name,count]]} for legend), what refs=true returns, and what renumber/bake do to tagging and dimension state. This is far beyond the baseline for fully covered schemas.

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 'Change the plan annotations' names a specific verb and resource, and the closing sentence 'The annotations tool reads them' explicitly separates this mutating tool from its read-only sibling. The different modes (anchor, dims, refs, legend, bake) all fall under the single purpose of changing plan annotations, so an agent can tell what the tool is for.

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 mode-level conditions, such as 'run it while the numbers are still right' for anchor and 'renumber=true numbers them again in reading order', and points to the annotations tool as the reader. But it never states directly when to choose edit_annotations over the sibling edit_* tools or when not to use it, leaving much of the selection inference to the agent.

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