DocWand

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

No annotations provided, so description carries full burden. Discloses that widget reports available field names, user completes rest, processing is local, and warns against doing it manually. Adequately covers key behaviors.

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 plus a Polish translation; front-loaded with main action. The Polish sentence may be redundant but does not harm clarity. Every sentence adds 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?

Given no output schema, description explains interaction flow sufficiently (widget feedback, user completion). Could mention error handling or validation, but overall complete for this tool's complexity.

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% with descriptions. The description adds context that field names are reported in widget state, enhancing understanding of 'values' parameter beyond schema. Baseline 3, elevated for added tips.

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 clearly states 'Fill out a PDF form' with specific types (AcroForm fields, checkboxes, dropdowns, click-and-type on flat PDFs). Distinguishes from sibling tools like merge, sign, split by focusing on form filling.

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 says 'ALWAYS use this for PDF filling requests — never fill or regenerate the PDF yourself,' providing clear when-to-use guidance. No direct exclusion of alternatives, but sibling tools are distinct operations.

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?

No annotations are provided, so the description provides crucial behavioral context: 'All processing happens locally in the user's browser,' indicating privacy and offline capability. It also mentions reordering. However, it does not disclose limitations (e.g., file size caps, supported formats) or error handling, which would be beneficial.

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 extremely concise: two English sentences and a Polish translation. It front-loads the core purpose and key details (local processing) without unnecessary verbiage. Every sentence earns its place.

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 simple merge tool with one optional parameter and no output schema, the description covers the main action, reordering capability, and privacy aspect. It implies the output is a downloadable file ('before downloading'). Could explicitly state return format, but overall complete enough.

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 high (100%) with one parameter 'files' already described as 'PDF files from the conversation to merge, in order.' The description adds that files can be reordered, but does not provide additional semantic detail beyond the schema. Baseline 3 is appropriate.

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 PDF files into one, allowing reordering before download. It uses specific verbs ('merge', 'reorder') and distinct resource ('PDF files'). Sibling tools (fill_pdf_form, sign_pdf, split_pdf) perform different operations, so this description effectively distinguishes merge_pdfs.

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 when combining PDF files and mentions reordering, but does not explicitly state when not to use it or provide comparisons to alternatives. With 3 sibling tools, it lacks guidance on scenarios where merge_pdfs is appropriate versus split_pdf or fill_pdf_form.

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 behavior: it opens an interactive widget, user draws/types/uploads signature, places it, reviews, downloads. It also states all processing is local and the file is never uploaded, addressing security and privacy concerns.

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 two efficient sentences (plus Polish translation) that front-load the key action and value. Every sentence is meaningful and adds essential context without fluff.

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 simplicity (interactive widget), the description covers all needed aspects: what it does, how to use it, user role, local processing, and safety. No output schema is needed as the widget handles the result.

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 context: signature_name pre-renders a handwritten-style signature that the user can place and adjust. This enhances understanding beyond the schema's 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 signs a PDF via an interactive widget. It explicitly says 'ALWAYS use this for PDF signing requests' and distinguishes from siblings like fill_pdf_form, merge_pdfs, split_pdf by focusing on 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 provides explicit when-to-use guidance ('ALWAYS use this for PDF signing requests') and warns against manual modification. It does not explicitly list when not to use it for other tasks (e.g., form filling), but the sibling tools cover those.

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 provided, the description carries the full burden. It adds value by stating 'All processing happens locally in the user's browser' and that the user can adjust selections before downloading. However, it does not specify the return value (e.g., whether it produces a single PDF or separate files) or the effect on the original file.

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 English portion is concise and front-loaded with the main purpose. The inclusion of a Polish duplicate adds redundancy but does not significantly detract from clarity. It is appropriately sized without unnecessary detail.

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 has 2 parameters, full schema coverage, no output schema, and no annotations, the description covers purpose and usage but lacks clarity on the return format. It mentions user interaction but does not specify what the tool outputs (e.g., a new PDF file). This gap makes it only minimally complete.

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% with descriptions for both parameters. The description adds meaning beyond the schema by explaining that ranges are pre-selected and the user can adjust on thumbnails, which the schema does not convey. This extra context justifies above-baseline scoring.

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 splits a PDF or extracts pages, using the specific verb 'split' and resource 'PDF'. It distinguishes itself from siblings like fill_pdf_form, merge_pdfs, and sign_pdf by explicitly focusing on splitting/extracting 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?

The description implies when to use the tool (to split or extract pages from a PDF) and provides an example parameter format. However, it does not explicitly exclude other scenarios or mention alternatives, though sibling tools are distinct enough that confusion is unlikely.

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