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

Annotations only flag destructiveHint=true and idempotentHint=false; the description goes far beyond by disclosing transactional semantics (stale version fails with DECK_CONFLICT before touching anything), atomic batch abort on paid backgrounds unless confirmDropPaid:true, re-render scope ('only edited slides'), automatic text re-fit, the `design` return payload, and cost ('FREE'). This is exactly the extra context an agent needs to avoid blind writes.

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 is front-loaded, then ops are grouped under Copy/Design/Structure, then constraints. Dense and long for a single paragraph but sized appropriately to a 13-variant operation union, with little filler.

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 destructive, non-idempotent batch tool with no output schema, the description covers conflict handling, atomicity, paid-resource safety, return shape, and render behavior. Minor gaps remain: no ordering guarantee for ops, no mention of the Canvas side effect implied by projectId, and no error taxonomy beyond DECK_CONFLICT.

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 only 43%, and the description compensates meaningfully: it explains the deck-wide-unless-slideId scoping rule, that apply_template keeps copy, that set_background_url is restricted to allowlisted AIGE/Storage hosts, and which external tool supplies font families. It leaves the large nested background recipe (light, objects, layers) and top-level locale/accountHandle/projectId unexplained, though some are covered by schema descriptions.

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 verb and resource ('Apply a bounded batch of edits to a deck') and enumerates the three op families (copy, design, structure), making the scope concrete. It does not explicitly distinguish itself from the many per-slide sibling tools (antix_set_slide_copy, antix_set_deck_fonts, antix_reorder_slides), so an agent must infer that this is the batch alternative.

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?

Useful prerequisites are given: expectedVersion must come from a prior antix_get_deck read, design values come from antix_list_carousel_design_options, and the agent is told to ask the user before setting confirmDropPaid. However, there is no explicit when-to-use-this-vs-siblings routing against the overlapping single-slide tools, so the choice is only implied.

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