pdf-tools

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

With no annotations, the description carries the behavioral disclosure burden. It adds 'Returns base64', which is useful, but does not clearly state whether the original file is modified, whether a new PDF is produced, or any error conditions. Some behavior is disclosed, but the mutation/return semantics are 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 short sentences with no filler; the main action is front-loaded and the output encoding is stated next. Every word 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 moderate-complexity PDF transformation, the schema documents all parameters and the description supplies the output format. It is complete enough for an agent to invoke successfully, though it could note whether the input file is replaced or a new PDF is returned.

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%, so the description need not repeat parameter details. The description does not add anything about the parameters beyond what the schema provides, which is acceptable given the baseline for full coverage.

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?

States a specific verb ('stamp') and resource ('every page of a PDF'), and the sibling tools are all distinct PDF operations. The purpose is immediately clear and unambiguous.

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 conveys the intended use by naming the operation, but it does not explicitly mention when to choose it over watermark_pdf or other siblings. Usage is implied rather than stated as a decision rule.

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 carries the behavioral disclosure burden. It usefully discloses that a new PDF is produced with original page order and that the return value is base64, but it does not mention side effects on the input, invalid page handling, or error cases.

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, dense sentence that conveys the action, the scope, the ordering behavior, and the return format with no wasted words. The most important information is up front.

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 two-parameter tool with complete schema coverage, the description provides the key behavioral facts: extraction into a new PDF, original order preservation, and base64 return. It does not cover edge cases or error behavior, but the core calling context is sufficiently 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?

The input schema already documents both parameters fully, including the base64 format and page list syntax. The description adds no additional parameter-level detail, so the schema carries the explanatory weight and the baseline score applies.

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 states a specific verb ('Extract'), a resource ('pages'), and the result ('a new PDF'), making the operation clear. The phrase 'original order' adds useful precision and helps distinguish this from related tools like remove_pages or 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 the tool is for creating a new PDF from a subset of pages in their original order, but it does not explicitly state when to prefer it over alternatives like remove_pages or split_pdf. Usage context is inferable but not directly spelled out.

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 discloses that the operation is a destructive, non-editable transformation ('permanent page content', 'answers can't be edited') and states the return format ('Returns base64'). It lacks details about irreversibility or side effects, but the core behavior is clearly disclosed.

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 sentence that front-loads the action and effect, then adds the essential return format. Every word earns its place with no redundancy.

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 single-parameter tool with no output schema, the description is nearly complete: it explains the transformation, the permanence of the output, and the return format. It could mention irreversibility or input requirements, but the schema covers the size limit and the description covers the core behavior.

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%, and the schema already documents both the base64 encoding and the 10 MB limit. The description adds no parameter-level detail beyond identifying the input as a PDF, so the baseline of 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 uses a specific verb and resource ('Flatten fillable form fields into permanent page content') and clearly states the intended effect. It is distinct from all sibling PDF tools, none of which relate to flattening forms.

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 conveys the purpose and the outcome ('so answers can't be edited'), which implies when to use it. It does not explicitly name alternatives or exclusion conditions, but the tool is unique among the siblings, so the context is sufficient.

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?

Annotations are absent, so the description must carry the behavioral burden. The verb 'Read' implies no modification, but the description does not explicitly state that the file is unchanged, what the return structure looks like, or potential errors (e.g., invalid PDF). This is adequate for a simple getter but not fully 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?

A single, well-structured sentence that leads with the verb and resource, then concisely lists the relevant metadata fields. No filler or redundancy.

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 tool is simple and the schema covers the only parameter, but with no output schema and no annotations, the description should ideally state what the returned metadata looks like (e.g., a structured object) and confirm the operation is non-destructive. It is complete enough for basic use but leaves some ambiguity.

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 the single 'file' parameter and its base64/max-size details. The description adds no extra meaning about the parameter itself, just about the output, so the baseline 3 applies.

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 ('Read'), a clear resource ('a PDF's document properties'), and enumerates the exact fields (title, author, subject, keywords, etc.). It is unmistakably distinct from sibling tools like set_pdf_metadata and the page-manipulation tools.

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 context is clear: use this when you need to inspect a PDF's metadata. It does not explicitly name alternatives or state when not to use it, but the read-only intent and the sibling set_pdf_metadata make the intended usage obvious enough.

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 exist, so the description carries the full burden. It discloses order preservation and base64 return, but does not mention whether originals are left untouched, size limits on output, or error behavior. Nothing contradicts, but for a tool that creates a new file, more side-effect context would help.

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?

A single sentence that front-loads the operation and includes the key behavioral detail (order) plus return format. No filler or redundancy.

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 one-parameter tool with full schema coverage and no output schema, the description covers what an agent needs: input type, order semantics, and return format. It does not mention edge cases like output size or metadata, but those are not essential for correct invocation.

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 baseline is 3. The schema already documents base64 encoding, 10 MB max per file, 2+ files, and merge order. The description only echoes 'order given' and adds the return format, adding no new parameter meaning.

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?

States a specific verb (merge), resource (PDF files), order sensitivity, and output format (base64). Clearly distinguishable from sibling tools like split_pdf or extract_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?

Does not explicitly state when to use this tool versus alternatives. The intended use is strongly implied by the name and sibling set, but no conditions, prerequisites, or exclusions are 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?

There are no annotations, so the description carries the burden. It does disclose the destructive nature ('Delete') and the output format ('Returns the remaining document as base64'), which is helpful. However, it does not mention edge cases like invalid page ranges, page ordering, or effect on PDF metadata.

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 concise sentence that front-loads the primary action and includes the important return format. No filler or redundant words.

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 simple two-parameter tool and fully covered schema, the description covers the core operation and output. However, the lack of usage guidance, alternatives, or edge-case warnings leaves an agent uncertain about selection among sibling tools and behavior on invalid input.

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 both `file` and `pages`. The description adds no parameter-level detail beyond what the schema provides, matching the baseline for fully covered schemas.

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 action ('Delete') and the resource ('the given pages from a PDF'), and even mentions the return format. However, it does not explicitly differentiate the operation from siblings like extract_pages or split_pdf, so it is clear but not fully distinguishing.

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 gives no guidance on when to use this tool versus alternatives such as extract_pages, split_pdf, or rotate_pdf. The intended use is implied by the action, but there are no explicit conditions, exclusions, or comparisons with sibling tools.

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 carries the behavioral disclosure burden. It reveals the clockwise orientation, default page scope, and that the tool returns base64, which implies a transformation rather than an in-place modification. It could add side-effect or permission details, but the core behavior is 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?

Three tightly written sentences, each adding distinct information: the operation, the default scope, and the return format. No filler or redundant restatement.

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 tool with three parameters and no output schema, the description covers the key invocation details and the return type. It does not describe output structure beyond base64, but that is sufficient for an agent to call the tool and handle 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 moderate at 67%, and the description adds meaning beyond the schema: it specifies clockwise direction for degrees and clarifies that omitting pages rotates the entire document. The page-list example '1, 3' gives useful concrete syntax guidance.

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?

States a specific verb and resource: rotate pages by fixed clockwise degrees. The operation is distinct from all siblings, which handle extraction, merging, splitting, flattening, metadata, or watermarking.

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 clearly defines the default behavior (rotate all pages) and the condition for a narrower operation (provide a page list). It does not explicitly name alternatives or exclusions, but no sibling performs rotation, so the intended use is clear.

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 carries the full behavioral burden. It discloses the tool's mutating/transformative nature, the empty-string stripping behavior, and the base64 return format. It does not cover side effects or error handling, but the essential agent-relevant behavior is present.

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 short sentences with no filler. It front-loads the core action, then adds a practical usage tip and the return format. Every clause 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?

Given the low schema coverage and lack of output schema, the description covers the return format and a main use case, which is sufficient for basic invocation. However, it leaves ambiguity about what happens when optional metadata parameters are omitted and does not explicitly orient the agent toward get_pdf_metadata as the read counterpart.

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 low at 29%, but the description adds one important value-level semantic: empty strings strip metadata. Parameter names like title, author, and keywords are self-explanatory, and the schema documents file and keywords format. The description partially compensates for the coverage gap but does not explain omitted-parameter behavior.

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 states a specific action ('Rewrite') on a specific resource ('PDF's document properties'), which clearly defines the tool's function. This also differentiates it from siblings like get_pdf_metadata and the page-manipulation tools without needing to open their schemas.

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 a concrete use case: 'Pass empty strings to strip identifying metadata before sharing.' However, it does not explicitly say when to prefer this tool over get_pdf_metadata or mention alternatives, so the routing guidance is only implied rather than stated.

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 carries the disclosure burden. It does disclose the base64-file return format and default page-splitting behavior, but it does not state whether the input PDF is modified, how the returned files are structured, or any failure/limit behavior.

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 concise sentences with a concrete example, the default behavior, and return format. Every clause earns its place and no filler is present.

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 two-parameter tool, the description covers input format, range syntax, default behavior, and return type. It could improve by adding sibling-tool routing or an example of the returned base64 structure, but nothing essential is missing.

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 schema already covers the parameters, but the description adds meaning by explaining that each comma group becomes one output PDF and that omitting ranges yields one PDF per page. This goes beyond the schema's terse examples.

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?

States a specific action ('Split a PDF into parts') and defines the output granularity with range syntax. It is clear but does not explicitly distinguish itself from the similar extract_pages or remove_pages siblings.

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?

Provides two clear usage modes: supply comma-separated ranges for grouped outputs, or omit ranges for one file per page. It does not explicitly state when to prefer this over sibling tools, but the usage context is unambiguous.

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 carries the burden. It discloses useful behavior: diagonal placement, all pages, and base64 return. It does not state whether the operation modifies the original file or returns a new watermarked PDF, which is a meaningful side-effect gap.

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?

One short sentence front-loads the action and output. No filler; every phrase adds information, and examples make the tool immediately understandable.

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 low-complexity tool with fully described parameters, the description is nearly complete: input and output formats are indicated and all constraints are in the schema. The only notable omission is explicit confirmation that a new file is returned rather than the original being mutated, so it is not fully 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%, so the schema already documents all 5 parameters with types, defaults, and constraints. The description adds only example values and the 'every page' effect, which is helpful but not needed for parameter meaning.

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 ('Stamp') and resource ('watermark across every page'), distinguishes the behavior (diagonal, every page) and gives concrete example text. It clearly differentiates from sibling PDF operations like splitting or merging.

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?

It conveys an implied use case: adding a label like 'CONFIDENTIAL' or 'DRAFT' to a full PDF. However, it never explicitly says when to prefer this over siblings or mentions non-use cases, so guidance remains implicit rather than explicit.

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