ppt_modify_ooxml

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

No annotations are provided, so the description carries the full behavioral burden. It adds one valuable disclosure: 'Creates safety backup before mutation,' which is important for a destructive tool. However, it does not explain what 'Controlled' means, whether the backup is restored automatically on failure, how to revert to the backup, or what happens to prior edits — leaving significant behavioral surface undisclosed for a mutation tool with zero annotation coverage.

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 short sentences with the purpose front-loaded and the safety backup fact as a separate clear note. No wasted words. It loses one point only because the phrase 'low-level OOXML manipulation helper' is slightly redundant with the tool name and could have been spent on more unique value.

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?

This is a complex, destructive 15-parameter tool with 0% schema coverage, yet the description covers only general intent and the backup behavior. It does not document the operation set, the selection model, the validation/control guarantees behind 'Controlled,' or the interplay between parameters. Even with an output schema present, an agent cannot reliably construct a correct call for anything beyond the simplest gradient/shadow case.

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% with 15 parameters, so the description must compensate. It groups some params by feature category (gradients, transparency, shadows) but never explains the core control parameters: what 'operation' values exist beyond the default 'set_attribute', how selection works across slide_number/shape_id/xpath, the format of attributes and xml_fragment, or presentation_path semantics. For an agent, these are the load-bearing parameters and they are entirely unexplained.

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 names a specific verb+resource: 'Controlled low-level OOXML manipulation helper' for 'gradients, transparency, drop shadows, and raw XML manipulation.' This is specific about what it does and hints at its lower-level nature relative to siblings like ppt_modify_shape, but it doesn't explicitly name which sibling it is not, so the differentiation is implied rather than stated.

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 feature list (gradients, transparency, shadows, raw XML) implies it is for advanced or low-level manipulation needs, which gives some usage context. However, it never explicitly says when to use this versus siblings like ppt_modify_shape or ppt_apply_style, nor does it state when not to use it (e.g., 'for simple shape edits use ppt_modify_shape'). No alternatives are named.

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