DocWand

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

With no annotations, the description fully carries the burden of behavioral disclosure. It reveals critical traits: all processing happens locally in the user's browser, the widget reports field names, and pre-fill is limited to user-provided data. This helps the agent understand security and workflow implications.

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 with two main sentences front-loading purpose and usage. A bilingual line adds minor redundancy but does not significantly detract. Every sentence adds value, but the Polish translation could be omitted for brevity.

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 no output schema, the description should explain what the tool returns or how the agent obtains the result. It mentions the widget reports field names but does not specify whether the tool returns a modified file or only opens an interactive widget. The signature parameter behavior is vague. This leaves gaps for an AI agent to infer the return value.

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 coverage is 100%, but the description adds value beyond schema: it explains the interactive flow, that values should only contain user-provided data, and that field names are learned after load. The signature_name parameter is explained as 'handwritten-style signature,' which is already in schema but contextually reinforced.

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 fills out PDF forms using an interactive widget for AcroForm fields and flat PDFs. It distinguishes itself from siblings (merge_pdfs, sign_pdf, split_pdf) by emphasizing the interactive, local nature and specific use case.

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?

Explicitly states 'ALWAYS use this for PDF filling requests — never fill or regenerate the PDF yourself,' providing clear when-to-use and what-not-to-do guidance. Additionally, it explains that only explicitly provided data should be pre-filled and that the widget reports field names for user completion.

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

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

The description discloses that all processing is local (privacy) and that users can reorder files, but lacks details on error handling, file size limits, or authorization needs. Since annotations are absent, the description carries full burden and is partially adequate.

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 short and front-loaded with the main action, but includes redundant Polish text that duplicates the English content, wasting space. Otherwise efficient.

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?

With one simple parameter, no output schema, and no annotations, the description covers the core functionality and local processing. However, it lacks details on return value, constraints (max files/size), and error cases, leaving gaps for an agent.

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?

The input schema has one array parameter 'files' with a description. Schema coverage is 100%, so the description adds little beyond restating the parameter's purpose. No extra semantic detail provided in the tool description.

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 merges multiple PDFs into one, with ability to reorder. Name and purpose align, and it's distinct from siblings (fill_pdf_form, sign_pdf, split_pdf).

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 implies usage for merging PDFs and mentions reordering and local processing, but does not explicitly state when to use this tool versus alternatives like splitting or filling forms. No exclusion criteria given.

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

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

With no annotations, the description fully discloses key behaviors: opens a widget for drawing/typing/uploading, optionally pre-renders a signature, and emphasizes that all processing is local and the file is never uploaded. This is comprehensive and honest.

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 informative but includes a lengthy Polish translation that may be redundant for an English-speaking agent. The key information is front-loaded in the first sentence, but the bilingual structure adds verbosity.

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 no output schema, the description adequately covers what the tool does (opens a widget for user interaction and download) and its local processing nature. It is complete enough for an agent to understand the tool's behavior and expectations.

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?

The input schema has 100% description coverage, but the tool description adds value by explaining that signature_name renders a 'handwritten-style signature the user can place and adjust,' going beyond the schema's generic description. The file parameter is not further elaborated.

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 purpose as 'sign a PDF' and explains it opens an interactive widget for user input. It distinguishes from siblings like fill_pdf_form, merge_pdfs, and split_pdf by focusing specifically on PDF signing.

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 explicitly instructs to 'ALWAYS use this for PDF signing requests' and warns against signing or modifying the PDF directly, providing clear usage context. However, it does not explicitly contrast with siblings or mention when not to use it beyond the directive.

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

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

Discloses local browser processing (security trait) and user interaction on thumbnails, but lacks info on file size limits, error handling, or return format. With no annotations, description carries burden but is incomplete.

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 English sentences front-load core purpose and usage, followed by Polish translation. The translation is redundant for most agents, slightly increasing length but not harming clarity.

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?

Covers main functionality and local processing, but lacks details on output (e.g., interactive download) and error states. No output schema, so description should elaborate on result, which it does not fully.

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?

Description adds context beyond schema: explains ranges are for pre-selection and that user can adjust, complementing the schema's example. Both parameters are covered at 100% schema coverage, so credit for extra usage 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?

Description uses specific verb 'split' and resource 'PDF', and distinguishes from sibling tools like merge_pdfs and sign_pdf by focusing on extraction of pages.

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?

Implies usage for splitting PDFs with optional pre-selection via ranges, but no explicit when-not-to-use or comparison to alternatives. The mention of user adjustment hints at interactive use but lacks clear boundaries.

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