Apply Edits

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

The description discloses critical behaviors beyond annotations: one lock, one backup, atomic save, resolution of all locations before mutation, stale anchors refusing the whole batch with failed indices, and result.changed mapping op index to outcome. It also notes the absence of shape/table/slide insertion. These align with destructiveHint=true and add substantial safety-relevant context.

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 dense but exceptionally efficient: the first sentence summarizes the entire model, followed by compact bullet-like clauses for ops, anchoring, atomicity, backup, and usage routing. Every sentence adds necessary information with no filler or repetition.

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 complex batch tool with 0% schema coverage and no parameter enums, the description is remarkably complete. It covers the edit format, op list, anchor resolution, failure behavior, atomic constraint, backup option, and singles-out the standalone alternatives. An output schema exists, so return-value documentation is unnecessary, and the description even previews result.changed.

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%, so the description fully compensates. It explains the edits array format (op plus params addressed by anchor or explicit slide/shape/table keys), enumerates the available ops, clarifies text_anchor for format_text, and describes atomic and backup semantics. Only file_path is implicit, but its meaning is obvious from context.

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 description opens with 'Batch editor: many edits, one lock, one backup, one atomic save,' which precisely identifies the tool as a batch editing operation. It further differentiates from creation tools by stating 'These ops EDIT existing content; nothing here inserts shapes, tables, or slides.' This makes the tool's purpose unmistakable.

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?

Provides explicit guidance: 'Use this when a change needs two or more edits; for a single edit use the standalone tool...' It also explains that creation tools belong to packs via enable_tools, and that atomic must stay True because v1 has no partial-apply mode. This fully covers when to use the tool versus alternatives.

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