SmartPDF

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

No annotations are supplied, so the description carries the behavioral burden. It discloses useful operational details (defaults, the 6–72 font-size range, the public-URL requirement for file_url), but says nothing about whether the source file is modified, how the result is delivered, or any auth/limit constraints. With an output schema present, return values need not be explained, which keeps this at an adequate 3.

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 purpose line followed by five terse parameter lines, each front-loaded with the parameter name. No filler, no repetition of the schema structure.

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-purpose PDF mutation tool with an output schema and fully documented parameters, the definition is nearly sufficient. The remaining gap is guidance on when to choose this over watermark_pdf and whether the original file is preserved.

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, and it does: it documents all five parameters, names the three allowed position values, gives the font_size range 6–72 and default 12, the start_from default of 1, and an example prefix string. This fully covers what the bare schema omits.

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 opens with a specific verb+resource: 'Добавляет номера страниц в PDF' (adds page numbers to a PDF), which is unambiguous. It does not differentiate itself from the nearest sibling watermark_pdf, which also stamps content onto pages, so it stops short of a 5.

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?

There is no when-to-use guidance, no prerequisites (e.g. whether the PDF must be unprotected), and no mention of alternatives such as watermark_pdf for arbitrary stamps. Usage must be inferred entirely from the tool name and parameter list.

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 burden, and it does disclose the output shape ('Одно фото — файл, несколько — ZIP-архив') plus the pixel ceilings for each level, which is genuine behavioral context. It says nothing about whether the original is left untouched, permission/auth needs, or any rate limits, so the safety profile stays unknown.

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?

Four short lines, each carrying distinct information: formats, output multiplicity, level tiers, and the target_kb override. Nothing is repeated from the name or padded, and the parameter semantics are front-loaded where an agent will read them.

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 3-parameter tool with an output schema (so return values need no explanation), the description covers formats, output shape, tiers, ranges and parameter precedence. The remaining gap is tool-selection context against resize_image/compress_pdf and any note on original-file preservation.

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 0%, yet the description documents all three parameters: file_urls as public URLs, level with its three named tiers, default and resulting pixel dimensions, and target_kb with its 10–50000 range and its precedence over level. This fully compensates for the empty schema, including enum-like values the schema itself lacks.

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?

Specific verb + resource ('Сжимает фото') with an explicit supported-format list (JPG, PNG, WEBP, HEIC), which lets an agent separate it from compress_pdf at a glance. It stops short of naming an alternative (e.g. resize_image) or stating what it does not handle, so sibling differentiation is implicit rather than explicit.

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 gives real conditional guidance between parameters — 'target_kb ... тогда level не используется' clarifies that setting a target size overrides the quality level. There is no guidance on when to choose this tool over resize_image or compress_pdf, so tool-selection context is only implied.

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 carries the full behavioral burden and falls short. It notes that file_url is a public URL and that level defaults to medium, but says nothing about whether compression is lossy, how quality is affected, whether the output is a new file, or any permission/rate-limit constraints.

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 short lines, front-loaded with the core action followed by one line per parameter. Every sentence earns its place with no filler.

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?

An output schema exists, so return values need not be explained, and both parameters are covered. However, for a file-transforming tool with no annotations, the absence of any quality/lossiness note or usage context leaves a modest gap.

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, and it largely does: it explains file_url is a public URL and enumerates the level values low | medium | high with medium as the default. This adds meaning well beyond the bare string-typed schema, though it doesn't explain the tradeoff each level implies.

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 opens with a specific verb+resource ("Сжимает PDF-файл" / compresses a PDF file), which is unambiguous and clearly distinct from siblings like merge_pdfs or rotate_pdf. It does not explicitly name or differentiate itself from any sibling, but the action is self-evident from the name and first sentence.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives among the many sibling PDF tools. Usage is only implied by the tool name, so an agent gets no routing help beyond the purpose statement.

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 carries the behavioral burden. It usefully notes that format is preserved, that file_url must be public, and that EXIF rotation affects the box coordinates, but it omits supported formats, size limits, and whether the original is modified.

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 only two sentences and is front-loaded with the core action. Every line adds needed information without repetition or filler.

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 image crop operation with an output schema, the description covers the action, both inputs, and coordinate behavior. It is nearly complete, with only minor gaps around format limits and usage relative to sibling tools.

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 explain both parameters. It fully documents file_url as a public photo URL and box as [x0, y0, x1, y1] in 0–1 fractions from the top-left, including the EXIF rotation caveat.

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: 'Обрезает фото' (crops a photo) and notes format preservation. It clearly differs from crop_pdf by operating on an image, though it does not explicitly name or contrast with any sibling tool.

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?

There is no explicit guidance on when to use this tool versus alternatives such as crop_pdf, resize_image, or rotate_image. Usage is only implied by the tool name and parameter descriptions.

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 burden and does well: it discloses the non-destructive semantics ('содержимое за краем остаётся в файле') and the default behavior when box is absent. It does not mention permission/auth requirements, rate limits, or whether the output is a new file vs in-place edit.

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?

Front-loaded with the core action and default, then one line per parameter. Efficient and scannable; the box example is worth its length, though the redact_pdf aside could be folded more tightly.

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?

An output schema exists, so return values need no explanation. Given a 3-param mutation tool with no annotations, the description covers defaults, coordinate semantics, and the destructive-vs-non-destructive distinction well; only auth/permission context and output-format expectations are unaddressed.

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 0%, so the description must supply all meaning — and it does: file_url is a public URL, box is [x0,y0,x1,y1] in 0–1 fractions of the visible page with top-left origin and a concrete example, and pages is 1-based numbers or 'all'. This fully compensates for the empty schema descriptions.

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 ('Обрезает страницы PDF') and immediately defines the default mode ('без box — убирает белые поля автоматически'). It also names the sibling it is not (redact_pdf) for the data-hiding case, so an agent can distinguish it from the ~50 siblings without opening a schema.

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?

Gives an explicit when-to-use branch: omit 'box' to auto-trim white margins, supply 'box' for a specific region. It also names an explicit when-not and the correct alternative — 'для скрытия данных используйте redact_pdf' — which is the most likely misuse of a crop tool.

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 carries the full behavioral burden. It does not say whether the original file is modified in place or a new PDF is returned, whether the deletion is reversible, what the output is, or any permission/URL accessibility limits beyond a bare 'public URL' note. For a destructive mutation tool this is a substantial 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?

Three short lines, front-loaded with the action, then one line per parameter. Nothing redundant and no filler.

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?

An output schema exists, so return values need not be explained, and both parameters are documented. However, for a destructive mutation with zero annotation coverage, key facts — whether the source file is overwritten, and how the result is delivered — are 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?

Schema description coverage is 0%, so the description must compensate, and it does: file_url is defined as a public URL to the PDF and pages as a 1-based list of page numbers to delete. The 1-based indexing is genuinely useful information not present in the schema, though boundary behavior (out-of-range or duplicate indices) is unstated.

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: 'Удаляет указанные страницы из PDF' (deletes specified pages from a PDF). An agent can immediately tell this apart from extract_pages or reorder_pages by the destructive 'delete' verb, though the description never names or contrasts any sibling explicitly.

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?

There is no guidance on when to use this tool versus alternatives such as extract_pages (which keeps pages) or split_pdf, nor any prerequisites, exclusions, or ordering constraints. The agent must infer usage entirely from the name.

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 carries the full behavioral burden, and it discloses almost nothing: no file-size limits, no statement about multi-page handling or processing time, no indication of failure modes for malformed URLs. The only behavioral fact conveyed is that the input URL must be public (i.e., reachable without auth), which is a genuine but thin contribution. An output schema exists, so return values need not be explained, but the gaps above remain.

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 lines: the purpose first, then the one parameter's meaning. Every clause earns its place and nothing is repeated from the schema.

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-input format converter with an output schema already defining the return value, the description covers the essential facts: what it converts and what the input must be. It lacks only operational limits and error behavior, which is a minor gap given the tool's simplicity.

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, and it does: it identifies file_url as the public URL of the DjVu file, adding both the resource type and the accessibility requirement the bare 'string' schema omits. It stops short of giving URL format examples or size constraints.

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+resource: converts a DjVu book or scan into PDF. The format pair makes it distinguishable from the many sibling converters (epub_to_pdf, fb2_to_pdf, word_to_pdf) even without naming them explicitly. Not a 5 because it does not explicitly contrast itself with any alternative.

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 is implied by the format-specific name and the mention of 'book or scan DjVu' as the source material, but there is no explicit when-to-use, when-not-to-use, or alternative routing. For a single-purpose converter this is the minimum viable level.

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 and does a solid job: it discloses that whiteout deletes the underlying text from the file, that replace_text with empty text deletes the line, that objects stack in order (last on top), and that API signatures don't count toward the site limit. It omits auth/rate/error context and whether the source file is overwritten, but the critical destructive behaviors are surfaced honestly.

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?

Purpose is front-loaded in one line, then structured per object type; given 0% schema coverage the density is justified. It is long and dense, but nearly every clause carries required information rather than filler.

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?

An output schema exists so return values need not be explained, and the object-type reference compensates for the empty schema. What's missing is prerequisite/auth context and any when-to-use-vs-sibling routing, but for a complex 2-parameter tool the description is otherwise sufficient to invoke it correctly.

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%, and the description fully compensates: it defines file_url, the intent of objects (ordered, last on top), the fractional 0–1 coordinate system anchored top-left, the box format [x0,y0,x1,y1], point-based sizes, and the per-type fields (text wrap, font enums, colors, signature lines/image_url, point lists for line/arrow/ink, baseline for replace_text). This is meaning far beyond the bare array-of-objects schema.

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+resource set ('добавляет на страницы текст, подпись, картинку, закрашивание, пометки и фигуры') and then enumerates the exact object types it can place. This capability set is clearly distinct from the many conversion/utility siblings (watermark_pdf, add_page_numbers, compress_pdf); an agent can identify this as the general-purpose page editor without opening the schema.

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 is implied by the enumeration of capabilities, so an agent can infer 'use this when you need to place objects on pages'. However, it never states when to prefer edit_pdf over the overlapping siblings (sign_pdf for signatures, redact_pdf/watermark_pdf for overlays, replace_text vs a full redaction), leaving the boundary to inference.

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 usefully discloses that the input must be a public URL and that the output PDF gains a table of contents, but says nothing about processing limits, failure modes, or how the source book is handled.

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?

Very compact and front-loaded: purpose first, then the two parameters on separate lines. Every line carries information, though the parameter block is telegraphic rather than fully phrased.

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?

Both parameters are documented, the notable output trait (added table of contents) is mentioned, and an output schema exists so return values need not be re-explained. The remaining gap is operational context such as input restrictions or limits.

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, and it does document both parameters: file_url as a public EPUB URL and page with its a5 default (described as 'like a book') and a4 alternative. It adds real meaning beyond the bare string types, though it omits any constraints on the URL.

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 both resources (converts an EPUB book into a PDF) and adds a distinguishing output detail (with a table of contents). The source format naming clearly separates it from the many other *_to_pdf siblings (fb2_to_pdf, djvu_to_pdf, word_to_pdf, etc.).

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 never says when to choose this over the other conversion tools, nor does it state prerequisites or exclusions (e.g., DRM-free requirement, file-size limits). The only implied guidance is the page-size default, which is a formatting detail rather than usage context.

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 carries the full burden. It implies a non-destructive read (output is a 'new PDF'), but says nothing about whether the source is modified, permission/auth requirements, size limits, or error behavior for out-of-range pages.

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 compact lines, front-loaded with the purpose and followed by per-parameter notes. No filler, though the terse style leaves no room for usage guidance.

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?

An output schema exists, so return values need not be explained, and both parameters are covered. However, with no annotations and no usage or error guidance, the definition is only minimally complete for a tool that produces a derived file.

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 0%, so the description must compensate, and it does: file_url is documented as a public URL of the PDF, and pages as a 1-based list whose order is preserved. This adds real semantics the bare schema lacks, though duplicate/out-of-range handling is unstated.

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: 'Извлекает выбранные страницы в новый PDF' (extracts selected pages into a new PDF). This distinguishes it from delete_pages, reorder_pages and split_pdf, though it does not name those siblings explicitly.

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?

There is no explicit when-to-use or when-not-to-use guidance. With siblings like delete_pages, reorder_pages and split_pdf, the agent gets no criteria for choosing extract_pages over them; usage must be inferred from the verb alone.

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 adds real value by noting the output includes a table of contents and that file_url must be a public URL, but it omits permissions, rate limits, failure modes, or what the conversion produces beyond the TOC note.

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 terse lines, front-loaded with the purpose and then the two parameters. Every sentence contributes information with no repetition of the tool name.

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?

An output schema exists, so return values need not be described, and both parameters are covered in the prose. The main remaining gap is the absence of any behavioral detail an unannotated conversion tool might warrant, but for this simple two-parameter converter it is close to sufficient.

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, and it largely does: it defines file_url as a public FB2 URL (a meaningful constraint beyond 'string') and spells out the page values a5 (default, book-like) and a4. Enum values and the default semantics are conveyed in prose.

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 and resource pair — converting an FB2 book into PDF — plus a distinguishing output feature (a generated table of contents). This clearly separates it from generic converters, though it never names the format-specific siblings (epub_to_pdf, djvu_to_pdf) it is adjacent to.

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 is implied by the format pair rather than stated: an agent can infer this is the tool for FB2 sources, but there is no explicit when-to-use, no prerequisites, and no pointer to alternatives for other ebook formats.

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 and does well: it discloses the file is not mutated, that numbers are checksum-validated (SNILS, INN, cards), and that scanned pages without text are reported separately. It omits any auth, rate-limit, or file-size constraints, keeping it from a 5.

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?

Content is front-loaded with the core action first, then per-parameter notes, then the return shape. It is dense but every clause adds information; only the return-shape paragraph is somewhat verbose given an output schema already exists.

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 3-parameter detection tool with no annotations and an existing output schema, the description covers what the tool does, what it does not do to the file, which parameters exist, and even how the output boxes feed into redact_pdf. Nothing essential for correct invocation 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?

Schema description coverage is 0%, so the description must compensate and does: file_url is defined as a public PDF URL, kinds enumerates the accepted values and the default-all behavior, and words explains custom terms with the 3-character minimum. All three parameters gain meaning beyond the bare schema.

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 ('Находит персональные данные в PDF') plus the key constraint that the file is not modified, which separates it from mutating siblings like redact_pdf or edit_pdf. An agent can identify the operation without opening the schema.

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 gives a clear usage context — detection of personal data with checksum validation, file left unchanged — and points to the downstream workflow by noting that returned boxes can be passed to redact_pdf as areas. It does not explicitly contrast itself with alternatives like ocr_pdf or image_to_text, so it stops short of a 5.

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 does disclose the key trait that the result becomes non-editable and that form fields/annotations are baked in, which is useful consequence-level context. It does not cover permissions, input-file side effects, or processing behavior for a one-way transform.

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 short lines, front-loaded with the action, then the behavioral consequence, then the parameter. No filler. Slightly terse rather than verbose; nothing is wasted.

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 an output schema (so return values need no explanation), the description covers purpose, effect, and the one parameter's requirement. Adequate; only minor gaps around processing/permission behavior remain and those are lower stakes here.

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 0% (file_url is a bare string), so the description must compensate, and it does: 'публичный URL PDF-файла' adds the crucial requirement that the URL must be publicly reachable and the file a PDF. That is meaningful semantics beyond the schema's untyped string.

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 and clarifies what flatten actually does mechanically: 'впечатывает поля форм и аннотации в страницы' (bakes form fields and annotations into the pages). This is unambiguous and no sibling overlaps (none of the other tools flatten). It stops short of explicitly distinguishing itself from siblings, so 4 rather than 5.

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?

'идеально для госорганов и печати' (ideal for government agencies and printing) gives an implied use context for when the non-editable output matters, but there is no explicit when-to-use vs. alternative guidance (e.g., vs. protect_pdf or sign_pdf, which also touch form/annotation handling). Usage is inferred, not directed.

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 carries the full burden. It usefully discloses that the balance is shared across all keys and MCP, that included requests are consumed before balance, and that the tariff month resets at included_resets_at — but it never states whether this is a safe read-only call or whether invoking it costs anything.

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 purpose is front-loaded in the first clause, but the remainder is a dense block of field definitions that largely restate what the output schema already provides. It is informative but not tight.

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?

An output schema exists, so return values need not be explained, yet the description adds genuinely useful semantics (shared balance, depletion order, reset timing). For a zero-parameter read tool this is close to complete, missing only an explicit statement of side-effect safety.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The field explanations describe outputs rather than inputs.

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 ('Возвращает баланс API аккаунта') plus scope ('общий для всех ключей и MCP') and unit (rubles). It is unambiguously distinct from the PDF-manipulation siblings, though it never explicitly says so.

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 is only implied — an agent can infer you call it to check remaining credit or monthly spend. There is no explicit when-to-call guidance, no mention that the call itself may consume balance, and no reference to alternatives.

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, so the description carries the burden. It usefully discloses one real behavioral trait — that text remains text rather than being rasterized — which is not derivable from the schema, but it omits anything about reversibility, output characteristics, or file handling.

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?

Purpose is front-loaded and the parameter note is a single tight sentence. No wasted words, though the parameter line could be folded more cleanly into the flow.

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 one-parameter conversion tool with an output schema (so return values need no explanation), the description is largely adequate. Its main gap is the absent safety/behavioral profile, since zero annotations are provided.

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?

Single parameter at 0% schema description coverage, so the description must compensate. It does clarify that file_url is a public URL of the PDF, adding meaning over the bare 'string' schema, but gives no format or size constraints beyond that.

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+resource ('Переводит PDF в оттенки серого'), clearly distinguishing it from siblings like compress_pdf or flatten_pdf. The added note that text stays text further sharpens what kind of grayscale conversion this is.

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?

Gives a usage context ('для печати и требований «только ч/б»') that implies when to reach for it, but names no alternatives or exclusions (e.g. vs. pdf_to_pdfa or compress_pdf for print prep). Usage is implied rather than explicit.

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 does disclose genuinely useful behavior — the output shape changes depending on input count (JPG vs ZIP) — but says nothing about limits on the number of URLs, file size caps, failure handling, or permission/auth needs.

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?

Very tight and front-loaded: the core conversion behavior comes first, then per-parameter notes in a scannable list. Every line carries information; the slightly telegraphic style is the only minor cost.

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?

An output schema exists, so return values need not be documented, and the description still explains the output format distinction. For a 3-parameter conversion tool this is nearly complete; only operational limits and failure modes are absent.

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, and it largely does: file_urls is explained as public HEIC URLs (a real constraint the schema cannot express), compact as downsizing to 2000 px, and keep_metadata as preserving EXIF date/camera/geolocation. Only minor gaps remain, such as whether compact applies per-image or to the archive.

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: converting HEIC/HEIF iPhone photos to JPG, with the input format named precisely. The output rule (single photo → JPG, multiple → ZIP) further pins down the behavior and separates it from generic siblings like png_to_jpg or webp_to_jpg.

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 use case (converting iPhone HEIC photos) is implied clearly by the description, but there is no explicit when-to-use vs when-not guidance, no mention of alternatives, and no stated prerequisites beyond 'public URLs'. Nothing misleading, but nothing that routes the agent either.

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 must carry behavioral disclosure. It usefully states that file_url must be a public URL and documents default page size and orientation, but it does not cover auth needs, rate limits, output handling, or side effects.

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 front-loaded and minimal: purpose first, then parameter documentation. Every line earns its place and there is no repetition or filler.

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 conversion tool with an output schema, the description covers the purpose and all input parameters including defaults. It lacks usage routing among alternatives, but return-value details are unnecessary because an output schema exists.

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 fully compensates by documenting all three parameters: file_url as a public HTML URL, page_size with allowed values A4/A3/Letter and default A4, and orientation with portrait/landscape and default portrait.

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 and resource: converts an HTML file to PDF. It is immediately distinguishable from siblings like jpg_to_pdf, word_to_pdf, and pdf_to_word without needing to open the schema.

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?

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The name and purpose imply the basic use case, but the description does not route the agent among the many conversion siblings.

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 carries the full burden, and it does disclose meaningful behavior beyond the schema: cost (1,25 ₽ per 10 photos / 10 MB), that all photos are merged into a single output, and the semantic difference between txt (lines as in the photo) and docx (paragraphs). It omits things like async behavior or failure handling, but covers the operational essentials.

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 block is front-loaded (what it does, then cost, then per-parameter notes) and every line carries information an agent needs. No filler or repetition.

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 an output schema present, return values need no explanation, and the description covers purpose, pricing, input constraints, per-parameter semantics and output format behavior. Nothing required to invoke it correctly 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?

Schema description coverage is 0%, and the description fully compensates: file_urls is defined as public URLs with the allowed image formats, languages lists the four supported codes and the default ['rus','eng'], and format explains txt vs docx and the default. All three parameters gain meaning not present in the schema.

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: OCR of text on photos/images, with the concrete output ('все фото — в один TXT или DOCX'). The scope ('фото и картинках') and the reference to ocr_pdf make it easy to separate from the many pdf_*/image-conversion 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?

Usage is implied through the accepted input formats (JPG, PNG, WEBP, HEIC, TIFF, BMP) and the pricing parallel with ocr_pdf, but there is no explicit when-to-use/when-not or a direct routing sentence such as 'use ocr_pdf for PDFs'. Adequate but inferential.

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 carries the full burden. It does disclose two real behaviors — that each image becomes one page and that inputs must be publicly reachable URLs — but says nothing about ordering, size/limit constraints, authentication, or where the resulting file goes. Adequate disclosure for a simple converter, with visible 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?

Two short sentences, front-loaded with the operation and followed by the page-mapping rule and parameter note. No filler; a slightly more explicit input/output framing sentence would make it 5.

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?

An output schema exists, so return values need not be described. For a single-required-parameter conversion tool, the description covers the operation, the multi-image semantics, and the input format — everything needed to invoke it correctly.

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, and it does: it names file_urls and clarifies it is a list of public image URLs, which conveys both cardinality and accessibility requirements. Only the item type (string) is left to the schema.

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 ('Конвертирует изображения (JPEG, PNG) в PDF'), which is clearly distinct from sibling converters like html_to_pdf, word_to_pdf, and the reverse pdf_to_jpg. The only wobble is the name 'jpg_to_pdf' being narrower than the stated JPEG+PNG scope. It identifies the operation without explicitly routing against siblings, so a 4 rather than 5.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named despite a large family of sibling conversion tools. The agent must infer that this is the image-input path 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.

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

With no annotations, the description carries the full burden, and it does disclose a genuinely useful behavior beyond the schema: one image returns PNG, multiple images are bundled as ZIP. However, it says nothing about auth requirements, file-size or rate limits, or failure behavior for non-JPG/inaccessible URLs.

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, front-loaded with the core action and followed by the output-shape rule. Every sentence adds information; nothing is redundant.

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 conversion tool with an output schema present, the description covers the action, output shape, and input constraint adequately. Only permission/limits context is absent, which is minor here but leaves a small gap.

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, and it does: it explains that file_urls are public URLs pointing at JPG images, adding the 'public' constraint and the expected input format. It stops short of specifying array limits or per-item validation.

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 directional resource ('Конвертирует JPG в PNG'), which cleanly separates it from the reverse tool png_to_jpg and from jpg_to_pdf. It does not explicitly name any sibling, so it stops short of full differentiation, but the direction is 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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives among the many conversion siblings. The only contextual hint is the output-shape note (single vs multiple), which is behavioral rather than usage guidance.

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 behavioral burden. It usefully discloses that inputs must be public URLs, that at least two are required, and that input order determines page order. It says nothing about failure behavior (unreachable/encrypted/protected PDFs), size limits, or what happens if merging fails partway.

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 compact sentences with no filler, front-loading the core action followed by the ordering rule and the parameter constraint. Every clause adds information.

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?

An output schema exists, so return values need not be described. For a simple single-parameter merge tool the description covers the action, ordering behavior, and input constraints. The remaining gap is error/failure handling for bad or inaccessible URLs, which is minor given the tool's simplicity.

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 single undocumented parameter — and it does: file_urls is defined as a list of public PDF URLs with a minimum of 2 entries, and the ordering semantics ('order of files = order of pages') give real meaning the schema cannot convey. It stops short of format details such as whether the array must be non-empty strings or URL scheme restrictions.

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 and resource ('Объединяет несколько PDF в один' — merges several PDFs into one), which is unambiguous and clearly distinct from siblings like split_pdf or extract_pages. It does not explicitly name alternatives, but the operation itself cannot be confused with any sibling.

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 is implied rather than stated: the agent can infer this is the tool for combining files, and the 'minimum 2 files' note hints at a precondition. However, there is no explicit when-to-use vs. when-not-to-use guidance, no mention of alternatives such as split_pdf, and no prerequisites for the operation.

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 burden and does meaningful work: it discloses the invisible-text-layer side effect, the 100-page cap, and the cost model ('1,25 ₽ за каждые 10 страниц'). It omits error/permission behavior, but the operational traits it does disclose are exactly the ones an agent needs.

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?

Purpose is front-loaded, followed by limits/cost and then per-parameter notes. Every sentence contributes; the only slight inefficiency is splitting parameter hints into a trailing block rather than integrating them tightly.

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?

An output schema exists so return values need no explanation, and the description supplies limits, pricing, the large-file workflow, and both parameter meanings. It leaves auth/error conditions unstated, which is a modest gap for a paid conversion tool.

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 0%, so the description must document both parameters, and it does: file_url is described as a public PDF URL and languages is described with an example and a default ('русский + английский'). Minor gap is that 'public URL' accessibility constraints are not spelled out.

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+resource ('Распознаёт текст в сканированном PDF (OCR)') and adds the concrete effect ('Добавляет невидимый текстовый слой'), which separates OCR from the extraction siblings like pdf_to_txt. An agent can identify the operation without opening the schema.

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?

Gives clear context (scanned PDFs), an explicit size boundary ('До 100 страниц за раз') and names the alternative for overflow ('больший файл сначала разделите split_pdf'). It stops short of any when-not guidance versus related convert/extract tools, so it is strong but not exhaustive.

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 carries the full behavioral burden. It does disclose useful output behavior via the layout modes ('per-table' vs 'single-sheet') and implies only tables are extracted, but it omits permissions, size/page limits, and what happens when no tables are found.

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?

Purpose is front-loaded in the first sentence, followed immediately by the two parameter explanations. Every line 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 simple two-parameter converter with an output schema handling return values, the description covers purpose and both parameters adequately. It leaves gaps around error conditions and scanning/OCR scenarios, but nothing essential to calling it correctly is missing given the output schema exists.

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, and it largely does: it explains file_url must be a public URL and that layout offers 'per-table' (default) or 'single-sheet'. Both parameters gain meaning beyond the type-only schema, though edge cases (e.g. invalid URL, table-less PDF) are unaddressed.

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 gives a specific verb and resource: it extracts tables from a PDF and writes them to an .xlsx file. The word 'tables' usefully scopes the operation against generic PDF converters in the sibling list. It does not explicitly name an alternative, but the purpose is unmistakable.

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?

There is no statement of when to use this tool versus siblings like pdf_to_txt, pdf_to_word, or pdf_to_pptx, nor any prerequisites (e.g. PDF must contain real tables, not scanned images requiring ocr_pdf). Only the parameter formatting is addressed, not usage conditions.

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 burden, and it does disclose a key behavioral trait: the result is a ZIP archive with page-N.jpg naming, plus the allowed dpi values. It omits any notes on permissions, file size limits, or how multi-page PDFs are chunked beyond the naming convention.

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 short, front-loaded lines: purpose and output first, then the two parameters. No filler, nothing repeated from the schema.

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?

An output schema exists, so return-value explanation is not required, and the description still notes the ZIP shape. Purpose, output, and both parameters are covered; only explicit usage/routing guidance is missing for a simple 2-param converter.

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, and it does: file_url is clarified as a public URL to the PDF, and dpi's valid values (72 | 150 default | 300) are enumerated with the default. Both parameters gain meaning beyond the bare schema.

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+resource ('Конвертирует страницы PDF в JPEG') and even names the output artifact (ZIP archive of page-N.jpg), so it is immediately distinguishable from the reverse sibling jpg_to_pdf and the other converters.

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 says what the tool does but gives no when-to-use guidance, prerequisites, or routing against the many sibling converters (pdf_to_txt, pdf_to_pptx, etc.). Usage is only inferable from the name and output statement.

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 usefully discloses the OCR page cap (100 pages) and that OCR is billed like ocr_pdf, plus the requirement that file_url be public, but it says nothing about input size limits, failure behavior, or what happens to 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?

Three short lines, front-loaded with purpose followed by per-parameter notes; every sentence carries information. Slightly terse on the parameter lines, but no filler.

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?

An output schema exists, so return values need not be explained, and the description covers purpose, both parameters, OCR trigger, cost, and a page limit. It stops short of naming the sibling it overlaps with (ocr_pdf, pdf_to_txt) and omits any input-size guidance.

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, and it does: file_url is clarified as a public URL, and ocr is explained with its trigger condition, supported languages, page limit, and cost. That is substantial meaning beyond the raw boolean/string schema, though neither param's format constraints (e.g. URL format, defaults) is fully spelled out.

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 names a specific verb and resource (converts PDF to Markdown .md) and even enumerates the structures preserved (headings, lists, tables, links, bold/italic), which clearly separates it from pdf_to_txt and pdf_to_word. It does not explicitly name or route against those siblings, so it falls just short of the top tier.

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 gives a clear use context (for neural networks, knowledge bases, documentation) and a conditional instruction for the ocr flag (use it for scans without a text layer, Russian and English). No explicit when-not or named alternative is given, so 4 rather than 5.

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 carries the full behavioral burden, and it says almost nothing beyond the format conversion. It does not state whether the source file is preserved, permission/auth requirements, file-size limits, or how the converted artifact is returned, leaving key operational traits undisclosed.

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 short lines: purpose first, then the two parameters, each earning its place with no filler. Slightly terse on behavior, but well front-loaded and waste-free.

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?

An output schema exists so return values need not be explained, and both params are documented. For a tool with zero annotation coverage, though, the description leaves behavioral gaps (source preservation, limits, error handling) that an agent would want before invoking.

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, and it does: file_url is defined as a 'публичный URL' and version is unpacked into 1/2/3 mapped to PDF/A-1b/2b/3b with the default noted. This adds meaningful semantics the bare schema (no enums) does not carry.

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 ('Конвертирует PDF в PDF/A') and immediately clarifies the target format's purpose (long-term archival). An agent can distinguish this from sibling conversions like compress_pdf or pdf_to_word without opening any schema.

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 clear use-case context ('архивы, суды, госорганы'), which tells the agent when this conversion is appropriate. However, it names no explicit alternatives or exclusion conditions, so routing guidance is contextual rather than prescriptive.

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 burden. It usefully discloses that output is a ZIP archive and that conversion is lossless, but omits any information on permissions, page/size limits, or error behavior for what is effectively a file-conversion operation.

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 short, front-loaded lines – purpose first, then the two parameters – with no wasted prose. Efficient for a simple conversion tool.

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?

Parameters and the ZIP output are covered, and an output schema exists so return values needn't be detailed. What's missing is differentiation from pdf_to_jpg and any operational caveats, leaving a small gap for a tool in a crowded conversion family.

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, and it does: it defines file_url as a public URL to the PDF and enumerates dpi as 72/150/300 with 150 as default. This adds real meaning the bare schema lacks, though it doesn't explain the file_url format/constraints in depth.

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+resource (converts PDF pages to PNG) and adds useful qualifiers ('lossless', for schemas/screenshots). It does not, however, distinguish itself from the sibling pdf_to_jpg, leaving the agent to infer why PNG rather than JPG.

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 parenthetical 'for schemas and screenshots' hints at an intended use case but gives no explicit when-to-use/when-not guidance and never references the obvious alternative pdf_to_jpg. The agent must infer the choice between the two image-export 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?

No annotations are provided, so the description carries the burden. It does disclose a real behavioral trait — one slide is produced per PDF page — which is genuinely useful. However, it says nothing about permissions, file-size limits, processing time, or what happens with scanned/image-only PDFs.

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?

Very tight: conversion behavior and page-to-slide mapping come first, and the parameter note follows. Every sentence carries information; no filler.

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 single-parameter conversion tool with an output schema already declared, the description covers the transformation semantics and the parameter meaning. Only secondary details (input constraints, failure modes) are missing, which is acceptable at this 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 description coverage is 0% and the single parameter is documented only as a bare string, so the description must compensate. It does add meaning by specifying that file_url is a public URL of the PDF file, but omits any format, reachability, or size constraints beyond that.

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 both source and target formats ('Конвертирует PDF в PowerPoint (.pptx)'), which clearly separates it from siblings like pdf_to_word, pdf_to_jpg and the reverse pptx_to_pdf. An agent can pick this tool without opening the schema.

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?

No when-to-use, when-not, or prerequisite guidance is given. The name makes the general intent obvious, but there is no mention of file-size limits, whether the input must be a text-based PDF, or how this differs in applicability from e.g. ocr_pdf before conversion.

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 carries the full disclosure burden. It does add real behavioral context: UTF-8 encoding, per-page text layout, paragraph/column blocks, and per-word coordinates. It omits permission needs, size limits, and crucially whether scanned PDFs need OCR first — a significant gap for a text-extraction tool with zero annotation coverage.

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?

Front-loaded with the core action, then parameter definitions in a compact structured list. Every line earns its place; the mode sub-bullets are informative rather than padding.

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?

An output schema exists, so return-value explanation is not required. For a two-param file-producing tool the definition is mostly adequate, but the absence of any OCR/scanned-PDF guidance leaves a real routing gap when sibling ocr_pdf exists.

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, and it does: file_url is defined as a public URL of the PDF, and each of the three mode values is explained with its output shape. Minor gap — it does not clarify mode's default placement alongside the schema's default, but coverage of both params is solid.

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: extracts text from a PDF into a .txt file, and pins the encoding (UTF-8). This clearly separates it from pdf_to_word, pdf_to_excel, and pdf_to_pptx, which produce different formats. An agent can identify the tool's job without opening the schema.

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 mode enumeration implies when to choose text vs blocks vs words, which is useful implied guidance. However, it never states when this tool is the wrong choice — notably it does not point to ocr_pdf for scanned/image PDFs, which is the single most important routing decision here. Usage is implied, not explicit.

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 burden. It usefully discloses an OCR page cap (up to 100 pages), pricing parity with ocr_pdf, and Russian/English language support, which are real behavioral traits beyond the schema. It says nothing about authentication, the non-OCR conversion path, or failure behavior, so the disclosure is only partial.

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 tight lines: purpose first, then each parameter annotated inline with zero filler. Every sentence earns its place and the most important information is front-loaded.

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 two-parameter conversion tool with an output schema (so return values need not be described), the definition covers purpose, both parameters, and key operational limits. The main gap is the absence of any when-to-use-versus-alternatives guidance among the crowded sibling set.

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, and it does: file_url is defined as a public URL of the PDF and ocr is explained as the scanned-document text-recognition switch with language and page-limit context. Both parameters get meaning the bare schema lacks.

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 ('Конвертирует PDF в редактируемый Word-документ (.docx)'), and the explicit .docx output implicitly separates it from siblings like pdf_to_txt, pdf_to_markdown and pdf_to_pptx. It does not, however, name or route away from any sibling explicitly.

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?

There is no guidance on when to choose this tool over the many competing conversion siblings (pdf_to_txt, pdf_to_markdown, ocr_pdf, etc.). The only conditional statement ('скан без текста') describes when to set the ocr flag, not when to use the tool itself.

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 disclosure burden and does well: it states what compact destroys (EXIF and geolocation), what scan physically does (locate the sheet, correct perspective, whiten background), and how page sizing behaves. It does not cover limits (photo count, file size) or auth, but the transformation behavior is unusually well 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?

Front-loaded with the core purpose in the first clause, then a tight per-parameter breakdown — each line earns its place. Slightly dense, but there is no filler or repetition.

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?

An output schema exists, so return values need no explanation, and all six parameters plus the key behavioral transformations are documented. The only omissions are operational limits (max photos, size caps) and failure behavior, which the description never addresses.

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%, yet the description documents all six parameters: file_urls (public URLs, accepted formats, order = page order), page (a4|photo with meaning of each), compact (default true plus effect), grayscale, scan, and scan_color (bw|color with the scan-only constraint). It fully compensates for the empty schema and supplies the enum values the schema lacks.

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 ('Собирает фото с телефона в PDF: каждое фото — страница') and immediately clarifies the multi-page batching semantics, which cleanly separates it from sibling single-image converters like jpg_to_pdf and heic_to_jpg. Multiple input formats are named, so an agent knows the scope without opening the schema.

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 is implied by the functionality (combine photos into one PDF) and the description does constrain scan_color to 'только при scan', but there is no explicit when-to-use vs alternatives guidance — nothing tells the agent when to pick this over heic_to_jpg + jpg_to_pdf or how to handle single vs many photos. Minimum viable routing, one gap.

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 carries the full disclosure burden, and it does deliver two non-obvious behaviors: transparency is flattened onto a white background, and the output container varies (single image → JPG, multiple → ZIP). It stops short of covering failure modes or auth/rate-limit expectations.

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 short sentences, front-loaded with the core operation, then the two behavioral qualifications, then the parameter contract. No filler or repetition.

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?

An output schema exists, so return-value documentation is unnecessary, and the description usefully notes the conditional ZIP output. It is essentially complete for a one-parameter converter, with only edge-case behavior (invalid/unreachable URLs) left unstated.

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, and it does: it specifies that 'file_urls' are public image URLs, ruling out local paths or base64 payloads and pinning the expected source format as PNG. That is meaningful guidance beyond the bare array-of-strings schema.

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+resource pair ('Конвертирует PNG в JPG') with unambiguous directionality, which distinguishes it from the many sibling converters (jpg_to_png, webp_to_jpg, heic_to_jpg). An agent can select it without opening the schema.

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 is implied by the name and direction of conversion, but the description never states when to prefer this over the sibling alternatives (webp_to_jpg, heic_to_jpg) nor any prerequisites beyond the input being PNG. Adequate but leaves routing to inference.

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 carries the full behavioral burden. It does disclose one real constraint beyond the schema: the file must be reachable at a public URL. However, it says nothing about file size limits, processing time, async behavior, or authentication expectations for a remote conversion service.

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 compact lines, with the action front-loaded and the parameter note second. Every clause carries information; nothing is padded or redundant.

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 an output schema present, return values need not be explained, and the single input is adequately covered. Still, for a zero-annotation conversion tool that hands work to an external service, the description omits operational limits and failure conditions an agent would want before invoking it.

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% and the single parameter has no description in the schema, so the description must compensate. It does: 'file_url: публичный URL PPTX-файла' clarifies both the meaning (URL to the PPTX) and the accessibility requirement (public), which the bare 'string' type does not convey.

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 and resource ('Конвертирует презентацию PowerPoint ... в PDF') and names both accepted input extensions (.pptx/.ppt). The direction of conversion implicitly separates it from the sibling pdf_to_pptx, though it never explicitly contrasts with the other converter tools (word_to_pdf, html_to_pdf, xlsx_to_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?

Usage is only implied by the declared formats: an agent can infer it should be called when it holds a PPTX and wants a PDF. There is no explicit when-to-use statement, no prerequisites, and no routing guidance relative to the other 20+ conversion/pdf 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?

No annotations are provided, so the description carries the full burden. It usefully discloses the AES-256 encryption level and the distinction between user and owner passwords, but says nothing about permissions granted/restricted, whether an already-encrypted file is rejected, or what the operation returns/produces.

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?

Front-loaded purpose sentence followed by a tight three-line parameter glossary. No filler, no repetition of structured fields beyond what the 0% schema coverage requires.

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?

An output schema exists, so return values need not be described. However, for a file-mutating tool with no annotations, the description omits whether the result is a new file/URL or an in-place change, and whether permissions are configurable.

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 0%, so the description must compensate, and it does: all three parameters are annotated (public URL for file_url, open password for user_password, owner password marked optional for owner_password). It does not explain how owner vs. user passwords affect permission restrictions, which is the one remaining gap.

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 ('Защищает PDF паролем') plus the encryption standard (AES-256), which is enough to distinguish it from the sibling 'unlock_pdf' by implication. It does not explicitly name the opposite-operation sibling, so it falls just short of a 5.

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?

There is no statement of when to choose this tool versus e.g. unlock_pdf or sign_pdf, and no prerequisites (e.g. whether the PDF must be unprotected first, or whether an existing password is needed). Usage is only inferable from the name and parameter list.

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 burden and does well: it discloses that redaction truly deletes text, that 'clean' strips metadata by default, and that scanned PDFs have no text to find. It does not mention required permissions or file-size limits, but the destructive semantics are clearly surfaced.

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?

Front-loads the purpose and the key differentiator, then lists parameters compactly, ending with the scan edge case. Every sentence carries information; it is dense but not padded.

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?

An output schema exists, so return values need no explanation. The description covers purpose, all parameters with defaults, the OCR precondition, and the metadata-cleaning side effect — nothing an agent needs to invoke it correctly 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?

Schema description coverage is 0%, so the description must compensate, and it does so thoroughly — every one of the five parameters (file_url, kinds, words, areas, clean) is explained with meaning, defaults, and for kinds the concrete enum values (passport, snils, inn, phone, email, card, account). The areas format is even illustrated with an example object.

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?

Names a specific verb and resource ('Скрывает персональные данные в PDF') and goes further by explaining the mechanism — actually removes text rather than painting over it. This clearly distinguishes it from siblings like find_personal_data (which only locates) and ocr_pdf (which extracts text).

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 that without 'areas' the tool searches on its own, points to find_personal_data as a source of areas, and instructs the agent to run ocr_pdf first for scans. Clear contextual guidance, though it never explicitly contrasts itself with find_personal_data's non-destructive role.

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 carries the full behavioral burden, and it is silent on key mutation traits: whether the original file is overwritten or a new PDF is returned, and whether the operation is non-destructive. It discloses only the basic action.

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 short lines, front-loaded with the action followed by the two parameter notes. Nothing is padded and each line adds information.

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 output schema covers return values and both params are described, but for an un-annotated file-mutating tool the definition omits whether the source is modified in place or a new file is produced, leaving a meaningful gap 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?

With 0% schema description coverage the description must compensate, and it does define both parameters: file_url as a public PDF URL and new_order as a 1-based ordering with a concrete example ([3,1,2]). It stops short of stating whether new_order must be a full permutation of all pages or may omit/duplicate pages.

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 ('Переупорядочивает страницы PDF' / reorders PDF pages), which is enough to distinguish it from delete_pages, extract_pages, and rotate_pdf by the operation performed. It is clear but never explicitly contrasts itself with those 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?

There is no when-to-use, when-not-to-use, or alternative guidance at all. The description only states what the tool does, leaving an agent to infer that reordering is the intended selection versus, say, merging or splitting.

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 carries the full behavioral burden. It only says that a damaged PDF gets repaired; it says nothing about output behavior (new file vs. overwritten), limits on what can be repaired, permissions, or failure modes. This is a significant gap for an annotation-free tool.

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 the purpose front-loaded and the single parameter appended. Every clause earns its place; only the very terse parameter line feels appended rather than integrated.

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 (1 required param) and an output schema exists, so return values need not be explained. But with no annotations and only a one-clause behavior statement, the description leaves the repair semantics and limitations underspecified for the 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?

Schema coverage is 0%, so the description must compensate, and it does so partially by explaining file_url as 'публичный URL PDF-файла' — conveying both accessibility (public) and file type. However it adds no format, size, or validity constraints, so it is adequate but with gaps.

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+resource ('Восстанавливает повреждённый PDF') and adds the trigger condition ('не открывается или открывается с ошибкой'), so an agent can tell this apart from password-related siblings like unlock_pdf or protect_pdf. It stops short of naming an alternative, so it is clear but not fully differentiated.

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?

Gives a clear when-to-use condition: the PDF is damaged, won't open, or opens with an error. It does not state when NOT to use it or name alternatives among the many sibling PDF tools, so context is present but exclusions are absent.

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 burden and does well: it discloses supported formats, format preservation, output packaging (file vs ZIP), default percent (50), valid range (1–500), keep_aspect behavior (scales by the smaller dimension), and enlarge behavior (default false, smaller images are not stretched). It does not cover error handling or invalid URL behavior, but the core behavior is well 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 front-loaded with the core action and output format, followed by a compact parameter list. Every sentence carries useful information 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?

Given the tool's moderate complexity (6 parameters), the presence of an output schema (so return values need not be explained), and 0% schema description coverage, the description covers the essential behavior and most parameter semantics. It lacks explicit routing among siblings, but for calling the tool correctly it is nearly 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 description coverage is 0%, so the description must compensate, and it does for most parameters: file_urls (public URLs), percent (scale, range, default 50), keep_aspect (preserve proportions by smaller scale), enlarge (allow enlargement, default behavior for small images), and collectively width/height (pixels). Width and height defaults are not explicitly stated, but overall the description adds substantial meaning beyond the bare schema.

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 (resizes) and resource (photo), lists supported formats, notes format preservation, and clarifies output packaging (single file vs ZIP). This clearly distinguishes it from siblings like crop_image, rotate_image, and compress_image.

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 is implied by the description of parameters and behavior, but there is no explicit when-to-use guidance, no mention of when not to use it, and no named alternatives among the many sibling tools. The agent must infer that this is for dimension changes rather than cropping or compression.

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 carries the full behavioral burden. It does disclose useful context: format is preserved and output is packaged as a single file or ZIP for multiple inputs. It omits permissions, rate limits, failure behavior, and whether rotation is lossless.

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?

Compact and front-loaded: the operation and output rule come first, followed by a tight per-parameter list. Every line earns its place with no filler.

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?

An output schema exists, so return values need no explanation, and all three parameters are well documented. The only gap is the absence of routing guidance among the many sibling image/PDF tools.

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% with no enums, so the description must compensate, and it does: file_urls are public URLs, angle accepts 0|90 (default)|180|270 clockwise, and flip is horizontal|vertical applied after rotation. This supplies the enum values and ordering semantics the schema lacks entirely.

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 pair and resource: rotates and mirrors photos while preserving format. The 'фото' scope implicitly but clearly separates it from the sibling rotate_pdf, though the description never names that sibling explicitly.

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 is only implied by the subject matter; there is no guidance on when to choose this over resize_image, crop_image, or rotate_pdf, nor any prerequisites. The output-packaging note (single photo -> file, multiple -> ZIP) is contextual rather than a selection hint.

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 carries the full burden. It is a mutation tool, yet nothing is said about whether the original file is overwritten or a new one is returned, permission/auth requirements, size limits, or rate limits. Only parameter syntax is 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?

Front-loaded one-line purpose followed by a compact parameter list with zero filler. Every line earns its place, though the parameter list reads more like schema restatement than prose guidance.

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?

An output schema exists so return values need no explanation, and all three parameters are covered. Still, for a mutation tool with no annotations, the description omits behavioral facts an agent needs (overwrite vs. new file, file-size or URL-access constraints).

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, and it does: it explains file_url is a public URL, pages is a 1-based list or "all", and constrains angle to 90|180|270 — a constraint absent from the schema. Only the distinction between the array and string forms of pages is left slightly implicit.

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 (rotates PDF pages), which is clearly distinct from siblings like reorder_pages or delete_pages. However, it never explicitly contrasts itself with those siblings, so the agent must infer the difference.

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 contains no guidance on when to use this tool versus alternatives such as reorder_pages or flatten_pdf, and no prerequisites (e.g. that the file must be reachable via a public URL). It only lists parameters.

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 carries the full burden. It does disclose the key behavioral trait that the signature is visual text (not a digital signature), which is valuable, but it omits whether the PDF is mutated in place, whether auth/quota is needed, or what happens on repeated calls.

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 purpose sentence followed by a compact parameter glossary; front-loaded and free of filler. The terse list style slightly reduces readability but is appropriately sized for seven parameters.

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 7 parameters, 0% schema coverage, and no annotations, the description covers parameter meaning but leaves behavioral and usage gaps (mutation semantics, relevance vs watermark_pdf). An output schema exists, so return values need not be explained.

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 0%, so the description must compensate, and it does: it documents file_url (public URL), signature_text, page (1-based), x/y coordinates on 0.0–1.0, and width/height block size on 0.0–1.0. This adds units and coordinate semantics absent from the bare schema, though it does not explain the defaults or which two are required.

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 and resource: it adds a visual text signature to a PDF page. The word 'визуальную текстовую' usefully distinguishes it from a cryptographic/digital signature, though it never explicitly contrasts with the sibling watermark_pdf, the closest neighbor.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as watermark_pdf. The agent is left to infer that this is a decorative overlay rather than a legal/cryptographic signing operation.

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 carries the full behavioral burden. It usefully discloses that the result is a ZIP archive and that file_url must be a public URL, but it omits other relevant traits such as permissions, rate limits, or whether the original file is untouched.

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 front-loaded with purpose and output, then documents parameters compactly. Every sentence earns its place with no redundant or filler content.

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 three-parameter schema, no annotations, and an existing output schema, the description is nearly complete for invocation. It clearly explains parameter meanings and the output format, though it still lacks sibling differentiation and broader operational 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%, and the description fully compensates by documenting all three parameters: file_url as a public PDF URL, mode values including the default, and the ranges format with an example.

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: 'Splits PDF into parts' and names the output format as a ZIP archive of PDF files. It does not explicitly distinguish the tool from close siblings such as extract_pages, so it falls short of a 5.

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?

There is no guidance on when to use split_pdf versus alternatives like extract_pages, delete_pages, or merge_pdfs. The mode options describe how to configure the split but not the tool-selection context.

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 carries the full behavioral burden. It says what the operation does but not whether the output is a new decrypted file, where it is returned, whether the original is preserved, or what happens on a wrong password. For a mutation-style tool with zero annotation coverage this is a meaningful 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?

Front-loads the operation in one sentence, then documents the two parameters in a compact list. Every line carries information; it is slightly terse rather than padded, which is appropriate here.

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?

An output schema exists, so return values need not be explained. However, for a tool with no annotations and no sibling-differentiation, the description leaves out error behavior and output handling, making 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 0%, so the description must compensate, and it does: it defines file_url as the public URL of the protected PDF and password as the password used to remove protection. This adds real meaning beyond the bare typed properties, though it omits format constraints such as URL scheme.

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: removes password protection from a PDF. It is clearly distinguishable from siblings like protect_pdf or flatten_pdf. It does not explicitly name the inverse tool (protect_pdf) to differentiate, so it falls short of a 5.

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?

No guidance on when to use this versus alternatives such as protect_pdf, nor any prerequisites (e.g. that the PDF must actually be encrypted, or that the password must be correct). The agent must infer usage from the name alone.

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 carries the full behavioral burden. It implies an additive write, but never states whether the watermark overwrites existing content, whether it is reversible, what permissions or file-state conditions apply, or any rate limits. Output schema exists so return format need not be covered, but the mutation/authorization profile is absent.

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?

Purpose is front-loaded in one sentence, followed by a tight parameter reference. No filler, no repetition. It is dense but readable, with each line earning 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 mutation tool with no annotations, the definition is only adequate: it covers inputs thoroughly but omits any behavioral/operational context (destructiveness, prerequisites, error conditions). The existing output schema relieves it of explaining return values, which keeps this from being lower.

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 fully — and it does. Every parameter is documented with meaning, defaults ('по умолчанию 0.3', 45), value ranges (0.0–1.0), the enumerated position options, and the text/image_url mutual exclusion.

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+resource ('adds a watermark to PDF pages'), which clearly distinguishes it from siblings like add_page_numbers, protect_pdf, and flatten_pdf. It's clear and unambiguous, though it never explicitly names an alternative tool to route away from.

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?

There is no explicit when-to-use or when-not-to-use guidance. The one piece of usage context provided is the mutual exclusivity between 'text' and 'image_url' ('excludes image_url' / 'excludes text'), which is useful but is a parameter constraint rather than selection guidance.

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 does disclose two genuinely useful traits: single input returns a JPG while multiple inputs return a ZIP, and the URLs must be publicly reachable. It says nothing about size limits, auth requirements, or failure behavior for unreachable/non-WEBP URLs, so disclosure is partial.

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, no filler, with the core conversion stated first and the output-format branching immediately after. 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 one-parameter conversion tool with an output schema already documenting return values, the description covers purpose, output packaging, and the input constraint. Only usage context and edge-case behavior are absent, which is a minor gap at this complexity level.

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% and the schema types file_urls only as an array of strings. The description compensates by specifying that these are public URLs of WEBP images, adding constraints (public accessibility, expected format) the schema does not convey.

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 and both source and target formats (WEBP → JPG), which cleanly separates it from the other format-conversion siblings such as png_to_jpg and heic_to_jpg. It also states the output packaging rule up front, so an agent knows exactly what the tool produces.

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 is implied by the format pair — call this when you have WEBP images to convert — but there is no explicit when-to-use statement, no exclusions, and no mention of alternative conversion tools. It is adequate but leaves routing entirely to inference from the name.

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 usefully discloses the branching output behavior (single page returns JPG, multiple pages return a ZIP), which is real value beyond the schema, but says nothing about size/page limits, error behavior, or that file_url must be publicly reachable.

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 tight lines with zero filler, front-loaded with the core conversion statement before the per-parameter notes. 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?

An output schema exists, so return-value detail is not required, yet the description still clarifies the JPG-vs-ZIP artifact. For a simple two-parameter, one-required tool this is nearly complete, with only error/limit behavior and auth requirements unaddressed.

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, and it does: file_url is explained as a public document URL (an important constraint) and dpi is given its valid values (72/150/300) plus the default. Both parameters are covered, though no format guidance for the URL itself.

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 (converts) and resource (Word documents: DOC, DOCX, ODT, RTF) plus the output (JPG images). An agent can immediately distinguish this from word_to_pdf or pdf_to_jpg without opening the schema.

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?

Format inputs are listed, so the applicable use case is implied, but there is no explicit when-to-use vs. siblings such as word_to_pdf or pdf_to_jpg, and no prerequisites or exclusions. Usage is inferred 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?

No annotations are provided, so the description carries the behavioral burden. It does disclose one important constraint - file_url must be a publicly accessible URL - which is real behavioral context, but it says nothing about file size limits, processing latency, failure modes, or whether the output is a download link. An output schema exists, so return format need not be explained, but other behavioral traits are missing.

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 lines, front-loaded with the verb and resource, followed immediately by the only parameter's meaning. No filler, no restatement of the tool name.

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 conversion tool with an output schema already describing the return, the description covers what an agent needs to invoke it correctly: direction, accepted formats, and the public-URL requirement. Missing size/limit and failure details keep it short of 5.

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% and the single parameter gets its own explanation: file_url is the public URL of the Word file. That adds genuine meaning the bare string-typed schema does not convey, specifically the public-accessibility requirement. It does not specify accepted URL schemes or size constraints, keeping it below 5.

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 names a specific verb and resource (converts a Word .doc/.docx document to PDF) and pins the accepted input formats, which distinguishes it from the many other *_to_pdf siblings. It stops short of explicitly naming the reverse sibling (pdf_to_word) or other converters, so it is clear but not sibling-differentiating.

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 is only implied by the stated conversion direction and accepted extensions (.doc/.docx); there is no explicit when-to-use, when-not-to-use, or route to an alternative such as html_to_pdf or jpg_to_pdf. An agent can infer the fit from the format constraint, but nothing is 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?

No annotations are provided, so the description carries the full behavioral disclosure burden. It only notes that file_url must be a public URL; it does not state file-size limits, authentication requirements, synchronous/asynchronous behavior, or other operational constraints.

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, front-loaded with the action and followed by the only parameter's meaning. No filler or redundant explanation.

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 one-parameter conversion tool with an output schema, the description covers the purpose and required input adequately. It is missing explicit usage guidance and operational limits, but the core invocation is clear.

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 single parameter. It does so by explaining that file_url is the public URL of an XLSX file, which adds useful format and access semantics beyond the bare string type.

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 and resource: converting Excel (.xlsx/.xls) to PDF. It clearly distinguishes this tool from siblings like pdf_to_excel, word_to_pdf, and html_to_pdf by naming both the source and target formats.

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 is implied by the conversion direction, but there is no explicit when-to-use guidance, no exclusions, and no mention of alternative conversion tools. An agent can infer the use case, but the description does not route between siblings.

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