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

The description adds significant behavioral context beyond annotations: the three modes, results included (names, types, dates, tags), and the note about REMARKABLE_ROOT_PATH restricting access. No contradictions with annotations (readOnlyHint, idempotentHint, destructiveHint).

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 well-structured with sections (usecase, instructions, parameters, examples), each sentence adds value, and it is front-loaded with the core use case. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 optional parameters, an output schema, and annotations covering read-only behavior, the description is complete. It covers all modes, path restrictions, and examples. No missing information that would hinder tool selection or 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 fully compensates by explaining each parameter's purpose (path for folder, query for search, tags for filtering), their defaults, and how they interact. Examples illustrate usage clearly.

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 explicitly states the tool's purpose: 'Browse your reMarkable library or search for documents.' It details three modes (browse, search, filter by tags) and provides clear examples, effectively distinguishing it from sibling tools like remarkable_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit instructions for when to use each mode (browse, search, filter), includes a note about the REMARKABLE_ROOT_PATH configuration, and gives examples. However, it does not explicitly differentiate from the sibling tool remarkable_search, which might lead to confusion about which search tool to use.

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

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

Annotations already indicate readOnlyHint=true and openWorldHint=false. The description adds that the canvas is read-only with page navigation and explains different behavior for clients with/without MCP Apps support, plus return of embedded PNG for non-interactive clients. No contradictions.

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 well-structured with clear <usecase>, <instructions>, <parameters>, and <examples> sections. Every sentence adds value without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, usage, parameter details, behavioral differences, and includes examples. It is complete for a read-only tool with interactive capabilities, though error handling or conditional behavior when document is not found is not mentioned.

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%, but the description adds meaning for both parameters: document can be name or path (with hint to use remarkable_browse), page is 1-indexed with default 1, and examples are provided. This compensates well for the schema's lack of 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?

The description explicitly states 'Open a reMarkable page in an interactive canvas viewer' and distinguishes from sibling remarkable_image for plain image extraction, giving a specific verb and resource with clear differentiation.

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 provides clear context for when to use this tool (interactive viewing) vs alternatives (use remarkable_image for plain extraction) and advises using remarkable_browse to find documents. It does not explicitly list exclusions but implies the alternative use case.

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

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

Annotations already mark destructiveHint=true, and the description reinforces this while adding substantial detail: items are moved to Trash by default, permanent=True removes the resolved UUID and sidecar files, confirmation is required unless skipped, and defer_restart triggers a refresh_pending flag. This significantly enriches the behavioral model beyond the annotation.

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 well-structured with usecase, instructions, parameters, and examples. Each section is dense with useful information without redundancy. The front-loaded usecase immediately states the purpose, and the instructions convey critical safety and mode details efficiently.

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 description covers all key aspects: default Trash behavior vs permanent deletion, mode availability (cloud/SSH, not USB), confirmation mechanics, parameter nuances, and example invocations. Even though an output schema exists, the description sufficiently contextualizes the operation for a destructive tool with mode-specific behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While the schema only lists titles and types, the description's <parameters> section explains each parameter in practical terms: 'document' is a name/path, 'permanent' is SSH-only and removes files permanently, and 'defer_restart' is SSH-only and skips restart to batch deletes. This fully compensates for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear statement: 'Delete a document or folder on the reMarkable tablet.' This specifies the verb (delete), the resource (document or folder), and the scope (reMarkable tablet), effectively distinguishing it from sibling tools like remarkable_move or remarkable_rename.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage context: it works in cloud and SSH modes (not USB web interface), is destructive by default, and explains when permanent deletion should be used ('only when the user explicitly asked for permanent deletion'). It also covers confirmation behavior and the defer_restart option, giving clear guidance on when and how to invoke the tool safely.

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

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

The description goes well beyond annotations by detailing that the output is written to a temporary directory, returned as a MCP ResourceLink (never base64 or arbitrary path), expires after 15 minutes, and may be evicted if more than eight exports are retained. It also explains PDF modes, Markdown behavior, OCR opt-in, and partial export handling. No contradiction with annotations (destructiveHint=false is consistent with 'without modifying the tablet').

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 uses a clear XML-like structure (usecase, instructions, parameters, examples) that is easy to parse. It front-loads the essential purpose and then goes into necessary detail. While verbose, every section adds value; minor trimming could improve conciseness without losing 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?

Given 4 parameters (1 required), no output schema, and moderate complexity, the description covers input requirements, behavioral details (resource lifespan, eviction policy), error handling (render failure placeholders), and usage examples. It leaves no significant gaps for an AI agent to infer.

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 compensates by listing each parameter in <parameters> with brief explanations (e.g., 'document: Document name or path (use remarkable_browse to find documents)') and provides three examples showing various combinations. However, it could add more detail about parameter interactions or constraints beyond what the schema enums already 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 <usecase> tag states 'Export one reMarkable document as a reusable PDF or Markdown file', providing a specific verb (Export), resource (one reMarkable document), and output format. This clearly distinguishes it from siblings like remarkable_read (read content), remarkable_browse (list documents), and remarkable_upload (import).

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 <instructions> explain that the tool exports a single document without modifying the tablet or its library, and the <parameters> section notes that the 'document' parameter can be found using remarkable_browse. While no explicit alternative comparisons are given, the context of sibling names and the detailed examples implicitly guide when to use this tool versus others.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well-covered. The description adds substantial behavioral context beyond annotations: details about merged PDF+annotation rendering behavior, response format differences (PNG as Blob, SVG as Text), compatibility fallback mechanism, OCR behavior (Google Vision vs local Tesseract), and legacy firmware limitations. This is comprehensive behavioral disclosure.

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 well-structured with clear sections (usecase, instructions, parameters, examples) and front-loaded purpose. However, it is somewhat verbose for an AI agent tool description—some details about OCR implementation (Google Vision vs Tesseract) and legacy firmware behavior could be in external docs or less critical for initial selection. Still, every section earns its place for a complex 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?

Given the tool's moderate complexity (7 parameters, 1 required, no output schema), the description is completely sufficient. It covers input semantics, behavioral details (merged rendering, response formats), error cases (legacy firmware), and provides examples for all key parameter configurations. The lack of output schema is compensated by clear explanations of what each format returns (BlobResourceContents, TextResourceContents, JSON with URI).

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 carries the burden of explaining parameters. It does so excellently: each parameter is described with default values, format requirements (e.g., hex codes for background), behavioral implications (render_merged values), and edge cases (transparent background notation). The examples provide concrete usage patterns that clarify parameter combinations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get an image of a specific page from a reMarkable document.' It specifies the verb (Get), resource (image of a page), and scope (from a reMarkable document). The use cases and examples further differentiate it from siblings like remarkable_read (text extraction) and remarkable_canvas (canvas manipulation).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool vs alternatives. The use cases section lists specific scenarios (viewing diagrams, getting visual context, etc.) and the examples cover common invocation patterns. The instructions explain when to use compatibility mode and include_ocr, and the parameters section clarifies when to use render_merged with different document types. Sibling tools like remarkable_export and remarkable_read are implicitly distinguished.

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?

Despite annotations only providing readOnlyHint: false, the description fully discloses behavior: it renders specific Markdown elements (headings, lists, tables, etc.), mentions that raw HTML is escaped and images are omitted, details transport-specific behavior (cloud vs SSH vs USB web), and states it requires write mode. There is no contradiction with annotations.

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 well-structured with clear XML tags (usecase, instructions, parameters, examples) and is appropriately sized for the complexity. Every sentence adds value, from rendering details to transport differences. No fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, multiple transports, rendering behavior, and an output schema), the description is comprehensive. It covers transport modes, parameter behaviors, rendering details, and prerequisites (write mode). The presence of examples further enhances completeness.

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 excellently. It explains each parameter with usage notes (e.g., 'Must not be empty' for markdown, defaults, transport-specific behavior like USB web ignoring parent_folder, and defer_restart being SSH-only and forwarded like remarkable_upload). This far exceeds what the schema alone provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb 'Render Markdown text as a PDF and upload it to the reMarkable tablet,' which precisely identifies the tool's function and distinguishes it from siblings like remarkable_upload (which uploads existing files) and remarkable_image (which handles images). The usecase tag reinforces the purpose.

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 <instructions> explicitly say 'Use this when the user wants notes, reports, summaries, or other Markdown content written back to the tablet without first creating a local file,' providing clear context. It also notes that this tool converts Markdown to PDF, uniquely positioning it among siblings like remarkable_upload which expect pre-made files.

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

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

Annotations only provide readOnlyHint (false), so the description carries full burden. It thoroughly discloses behavioral traits: mode differences, the need for xochitl restart in SSH mode, the effect of defer_restart, and the creation delay. No contradictions with annotations.

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 well-structured with clear XML tags (usecase, instructions, parameters, examples). Every sentence adds value—no fluff or repetition. It is appropriately sized for a tool with three parameters and mode-specific behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple modes, three parameters, one required), the description covers all necessary context: mode availability, restart behavior, parent path defaults, and batch hint. An output schema exists but is not needed to explain return values; the description is complete without 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%, so the description must compensate fully. It explains all three parameters in detail, including defaults, mode-specific behavior, and side effects (e.g., defer_restart sets refresh_pending). The examples show typical usage but do not edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Create') and resource ('a new folder'), and distinguishes this tool from siblings like remarkable_upload and remarkable_delete. The <usecase> tag clearly states the tool's primary function.

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 <instructions> section explicitly describes when to use the tool, including mode-specific behavior (SSH vs cloud) and a clear exclusion: 'Not available over the USB web interface.' It also references the sibling tool remarkable_refresh for batch operations, providing guidance on when to use 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?

The description transparently discloses that the operation is a mutation (readOnlyHint: false aligns with 'move') and explains the internal action: updating parent reference in metadata. It also reveals behavioral details for SSH mode, such as defer_restart skipping xochitl restart and setting 'refresh_pending': true. There is no contradiction with annotations.

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 well-structured with <usecase>, <instructions>, <parameters>, and <examples> sections, each serving a distinct purpose. Every sentence adds value—no fluff or repetition. It efficiently conveys purpose, prerequisites, mode restrictions, parameter details, and usage examples in a compact form.

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 output schema exists (relieving the description from explaining return values), the description covers all necessary aspects: purpose, prerequisites, mode compatibility, parameter semantics, and behavioral constraints. For a tool with 3 parameters and moderate complexity, this is fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema coverage is 0%, meaning no parameter descriptions exist in the schema. The description's <parameters> section fully compensates by explaining document ('Name or path'), dest_folder ('use "/" for root'), and defer_restart ('SSH only. Skip the xochitl restart...'). This adds substantial meaning beyond the schema's bare type definitions.

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 explicitly states 'Move a document or folder to a different location', using a specific verb and resource. It also explains the underlying mechanism ('updating its parent reference') and clarifies it works for both documents and folders. This clearly differentiates it from sibling tools like remarkable_rename or remarkable_delete.

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 instructs users to 'Find the document name with remarkable_browse() first', establishing a clear prerequisite. It specifies supported modes (cloud and SSH) and explicitly states unavailability over the USB web interface. It also explains when to use the defer_restart parameter (SSH only). However, it does not explicitly contrast when to use this tool versus alternatives like remarkable_rename, though the context of siblings makes it reasonably clear.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds rich behavioral detail: pagination mechanics (more, next_page, total_pages, content_pages, total_pages_known), content-specific behavior (text, raw, annotations), handling of older USB firmware, OCR provider fallback, and grep filtering. No contradictions with annotations. The description fully complements the safety profile.

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 long but well-structured with XML-like tags (usecase, instructions, parameters, examples). It is front-loaded with the core purpose. Every section serves a purpose: pagination details avoid context overflow, parameter explanations prevent misuse, examples show typical invocations. Could be slightly more concise by merging the <instructions> bullet on pagination into fewer sentences, but the organization makes it easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 parameters, pagination, content types, OCR, firmware edge cases), the description is thorough. It explains output fields like more, next_page, total_pages, content_pages, total_pages_known – and since an output schema exists, it doesn't need to enumerate all return values. It is slightly incomplete on error handling (what if document not found?) and does not mention rate limits or authentication requirements, but these may be covered externally. Overall, it leaves little ambiguity 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?

The input schema has 0% description coverage, so the <parameters> section in the description carries the full burden. It explains each parameter with clear semantic meaning: 'document' (name or path, use browse to find), 'content_type' (list of options with outcomes), 'page' (extracted-content page vs physical pages), 'grep' (regex on current page), 'include_ocr' (handwriting OCR). The examples further illustrate parameter usage. This adds significant value beyond the raw 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 opens with a clear '<usecase>Read and extract text content from a reMarkable document.' This specifies a concrete verb and resource. The three content types ('text', 'raw', 'annotations') further clarify what is returned. The tool is well-distinguished from siblings like 'remarkable_image' (image extraction), 'remarkable_export' (export as file), and 'remarkable_search' (search across documents).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides detailed instructions on pagination and grep filtering but does not explicitly state when to use this tool over its siblings. For example, it does not contrast with 'remarkable_export' or 'remarkable_image' for specific use cases. The parameter section advises using 'remarkable_browse to find documents', which implies a prerequisite, but it lacks explicit 'when/when-not' 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds valuable context: sorting order, preview behavior, and the ROOT_PATH filtering. No contradictions.

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 well-structured with usecase, instructions, parameters, and examples tags. It is front-loaded with the main purpose. While the XML-like tags add some verbosity, every section provides distinct value. Could be slightly more concise but not excessive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 2 simple parameters, complete annotations, and an output schema, the description covers all necessary aspects: use case, parameter details with limits, example invocations, and an environmental note. Nothing essential is missing for a list 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 description coverage is 0%, so the description fully compensates by detailing 'limit' with default, max values (50 without preview, 10 with preview) and 'include_preview' with content length (~200 chars). Examples further illustrate usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get your most recently modified documents.' with explicit verb+resource. It further specifies sorting by modification date (newest first). This distinguishes it from sibling tools like remarkable_search (query-based) and remarkable_browse (file listing).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: 'Use this to quickly find what you were working on recently.' It also mentions the REMARKABLE_ROOT_PATH restriction. However, it does not explicitly list when to avoid this tool in favor of alternatives, though the sibling tools context implies distinctions.

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

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

The description goes well beyond the readOnlyHint=false annotation. It explains the core behavior: 'Changes the display name of a document or folder by updating its metadata.' It also details the defer_restart parameter's effect: 'Skip the xochitl restart so a batch of writes can refresh once via remarkable_refresh() instead of once per write. Sets refresh_pending: true. Ignored in cloud mode.' No contradictions with annotations.

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 well-structured with dedicated sections (usecase, instructions, parameters, examples) and is front-loaded with the purpose. It is about 150 words, which is appropriate for the complexity. Minor room for trimming, but it's efficient and clear.

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, the description covers purpose, parameters, usage prerequisites, mode restrictions, and examples. It does not mention error handling or return values, but the presence of an output schema likely covers those. The description is complete enough for an AI agent to use the tool 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?

With 0% schema description coverage, the description carries the full burden. The <parameters> section explains each parameter: document (current name or path), new_name (new display name), and defer_restart (SSH only, restart behavior, ignored in cloud mode). This adds critical meaning beyond the bare schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Rename a document or folder on the reMarkable tablet.' It uses a specific verb (rename) and resource (document or folder), and the context of sibling tools like remarkable_move, remarkable_delete, and remarkable_upload makes it easy to distinguish from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides helpful usage guidance: 'Find the document name with remarkable_browse() first' and explains mode availability ('Works in cloud and SSH modes... Not available over the USB web interface'). It also describes the defer_restart parameter for batch operations. It does not explicitly list when not to use the tool, but the context is sufficient for an AI agent to decide appropriately.

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?

Description adds behavioral context beyond annotations: searches document names, optionally content with grep, returns summaries, max 5 docs, first page ~8000 chars. Annotations (readOnlyHint, idempotentHint) are consistent. No contradictions.

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?

Description is structured with XML tags (usecase, instructions, parameters, examples) that improve readability. Content is front-loaded with purpose. Each section adds value; examples are helpful. Could be slightly shorter but not 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?

Given 5 parameters, output schema exists, and sibling tools, the description covers purpose, parameters, limits, examples, and usage context. It explains output returns summaries from multiple documents. Adequate for an agent to invoke 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?

With 0% schema description coverage, the <parameters> section provides essential meaning: describes each parameter's purpose and default behavior (e.g., 'optional pattern to search within document content' for grep, 'Enable OCR for handwritten content' for include_ocr). Adds value beyond schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches across multiple documents and returns matching content, with specific verb 'Search' and resource 'Documents'. Examples further clarify usage. Distinguishes from siblings like remarkable_read (single document) and remarkable_browse (folder listing).

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 includes explicit usage guidelines: efficient for cross-document search, limits (max 5 docs, first page ~8000 chars), and filtering options. It doesn't explicitly state when not to use, but the context is clear from instructions and sibling tools.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds valuable context about what each transport can and cannot do, how export works (temporary local resource, never modifies tablet), and how to enable write mode. However, it could detail the returned capability matrix structure more explicitly.

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 well-structured with clear XML tags, front-loaded summary, and detailed sections for instructions and examples. It's longer than strictly necessary for a zero-param tool but each section adds value for agent decision-making. Could be slightly more compact.

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 zero parameters, present annotations, and existence of an output schema, the description provides everything needed: purpose, transport capabilities, troubleshooting context, and an example. The output schema handles return value details, so the description's coverage is 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?

There are zero parameters, schema coverage is 100%, so the description has no param details to provide. The baseline is 4, and the description includes helpful usage examples and context that compensates for the lack of parameters.

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 verb "check" paired with specific resources (connection status, active transport, write capabilities) makes the tool's purpose highly clear. It explicitly distinguishes itself from siblings which focus on file operations or rendering tasks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool: to verify connection, choose a transport, or troubleshoot. It offers detailed capability breakdowns per transport and explains why write tools are disabled by default, helping the agent decide between alternative transports.

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

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

The description reveals extensive behavioral traits beyond the readOnlyHint=false annotation: requires write mode, transport-specific behaviors (USB web ignores parent_folder, SSH supports defer_restart), and the consequences of restarts (destabilisation, refresh_pending). This fully informs the agent of side effects and 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?

The description is well-structured with XML tags (usecase, instructions, parameters, examples), front-loading the core purpose. Every sentence adds value, covering transport modes, batch patterns, and edge cases without redundancy. It is efficient and highly readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, 3 transports, batch behavior) and the presence of an output schema, the description is complete. It covers all parameters, transport-specific nuances, batch usage, and response hints, leaving no gaps for an agent to interpret.

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 compensates fully by explaining each parameter: file_path (absolute path), parent_folder (default '/', transport-honored), document_name (default filename without extension), and defer_restart (SSH-only, batch usage, response flag). It adds critical meaning absent from 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?

The description explicitly states 'Upload a PDF or EPUB file to the reMarkable tablet', using a specific verb and resource. It clearly distinguishes from sibling tools like remarkable_image (for images) and remarkable_markdown_to_pdf (conversion) by specifying supported formats and transport modes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool (uploading local files) and includes instructions for different transports and batch usage. However, it does not explicitly exclude alternatives like remarkable_image for image uploads, leaving a minor gap in when-not-to-use guidance.

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