pdf_compare

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal the cost per page ($0.01) and the two output formats (JSON or PDF), which are useful behavioral traits. However, it omits details such as file handling (read-only vs. writing to output_path), error behavior, or limits on PDF size. The description is honest but not deeply transparent.

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 a single, efficient sentence that states the core purpose, output options, and cost. It is front-loaded with the main action and includes the cost as a key decision factor. There is no filler or redundant phrasing, making it optimally concise.

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?

Given the tool's complexity (7 parameters, no output schema, no annotations), the description is incomplete. It covers the primary function and output types but leaves parameter semantics for dpi, threshold, output_path, and idempotency_key undefined. It also does not describe error conditions, return format details beyond 'JSON', or any limitations. An agent would need to guess or rely on the schema defaults without full context.

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 must compensate for the schema's lack of parameter explanations. It clarifies that file_a and file_b are local paths and that output can be 'json' or 'pdf', which maps to the output enum. However, it does not explain dpi, threshold, output_path, or idempotency_key, leaving these parameters semantically unexplained. The description provides partial value but insufficient coverage for a 7-parameter tool.

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 ('compare') with a clear resource ('two PDFs') and describes the method ('page by page') and outputs (JSON or diff PDF). It clearly distinguishes itself from sibling PDF tools like merge, split, or rotate, which perform different operations. No ambiguity remains about what this tool does.

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 description states the tool's function but does not explicitly say when to use it over alternatives or when not to use it. Since it is the only PDF comparison tool among siblings, the intended usage is implied but not articulated. No exclusions or alternative tool references are provided, so an agent has to infer the appropriate context from the description alone.

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