deskew_pdf

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

With no annotations, the description must carry the behavioral disclosure. It does state a key behavioral trait: output pages are rasterized. However, it does not mention whether the original file is modified, how the output file is named (though schema covers this), or any limitations like maximum angle or DPI effects. The description adds some value but leaves significant behavioral gaps.

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 concise and front-loaded: the first sentence states the core purpose, and the second adds a critical behavioral caveat (rasterization). Both sentences earn their place, with no redundant or filler content. This is exemplary conciseness.

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?

The description covers the core purpose and a key behavioral outcome (rasterization), and the schema fully documents parameters. While there is no output schema or annotations, the description is reasonably complete for a tool of this complexity. It lacks only minor details like whether it preserves metadata or creates a new file, but the schema's output_name parameter implies a new file. Overall, it is sufficient for an agent to understand the tool's function and main side effect.

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 schema already documents all parameters (dpi, file, max_angle, output_name) with descriptive text. The tool description does not add extra parameter semantics beyond what is in the schema, such as explaining the interaction between max_angle and detection accuracy. Baseline of 3 is appropriate when the schema carries the load.

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 clearly states the tool's function: automatically detecting and correcting tilted scanned PDF pages. It uses specific verbs ('detect and correct') and identifies the resource ('tilted scanned PDF pages'), and distinguishes itself from sibling tools like 'rotate' by emphasizing automatic detection. The note that output pages are rasterized further clarifies the tool's scope.

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?

Usage context is implied: the description indicates it is for deskewing tilted scans, but it does not explicitly state when to use this tool versus alternatives such as 'rotate' or 'rasterize_pdf'. No exclusions or alternative recommendations are provided, so the agent must infer the appropriate use case from the name and description.

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