Apply batch updates to a Google Slides presentation: insert, update, or delete slides, text, shapes, and tables. Deletions are permanent—no undo.
Apply updates to a presentation (insert/update/delete slides, text, shapes, tables, etc). Delete requests in a batch are permanent — the API has no undo.
| Name | Required | Description | Default |
|---|---|---|---|
| requests | Yes | Array of update requests as JSON string | |
| presentationId | Yes | The presentation ID |
Changes observed during successful MCP inspections.
v0.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the safety profile is known. The description adds a valuable specific behavioral fact beyond the annotations: 'Delete requests in a batch are permanent — the API has no undo.' This clarifies the permanence of deletes, which is more concrete than the generic destructive hint.
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?
Two sentences with no filler. The primary purpose is front-loaded, and the permanence warning is a critical behavioral note that earns its place. It is easy to parse quickly and contains only valuable information.
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 mutation tool with 2 parameters and no output schema, the description covers the essential call context: what the tool does and the key risk (permanent deletes). It does not mention return values or partial-failure behavior, but given the annotations already cover the safety profile and the schema covers the parameters, the gaps are relatively minor.
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 baseline is 3. The description adds meaning beyond the schema by enumerating what kinds of requests can be placed in the 'requests' array (insert/update/delete slides, text, shapes, tables), which helps the agent construct a valid request body. This exceeds the generic schema description 'Array of update requests as JSON string'.
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 uses a specific verb ('Apply updates') and a clear resource ('a presentation'), and enumerates concrete update types (insert/update/delete slides, text, shapes, tables). It clearly distinguishes this from read-only siblings like slides_get and slides_create by positioning it as the mutation entry point.
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?
The context of when to use this tool is clear: it is the content-mutation tool for presentations. However, it does not explicitly exclude adjacent cases, such as updating file metadata via drive_files_update, nor does it name alternatives. It earns a 4 rather than a 5 because the exclusions are left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.