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

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds valuable context about three operation modes, path relativity, and the effect of REMARKABLE_ROOT_PATH. 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-organized with sections (usecase, instructions, parameters, examples). While slightly verbose, each section serves a purpose and adds clarity. Slightly more concise presentation could improve scannability, but overall effective.

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 an output schema (not shown but present), the description covers all necessary aspects: modes, parameters, configuration note, and examples. It is complete for an agent to correctly select and invoke this 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%, but the description fully explains each parameter: path (default '/', folder navigation), query (optional, triggers search), tags (optional list, case-insensitive). Examples demonstrate 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 browses or searches the reMarkable library. It specifies three modes (browse, search, filter by tags) with examples. This distinguishes it from sibling tools like remarkable_search and remarkable_recent.

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

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

The description explicitly covers when to use each mode, including path navigation, search term triggering search mode, and optional tag filtering. It also notes the REMARKABLE_ROOT_PATH constraint. Examples cover all major use cases.

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 destructiveHint=true. The description adds that deletion is permanent, impossible to undo, and for folders all contents are deleted recursively. This provides valuable behavioral context beyond the 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 uses structured XML tags to separate sections, making it easy to parse. It is concise with no superfluous sentences, though the tag format could be streamlined. Each section serves a purpose.

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 destructive nature with one parameter and the presence of an output schema, the description covers all necessary aspects: purpose, permanence, recursion, verification suggestion, and examples. It is fully sufficient for the 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?

Schema has one parameter 'path' with no description (0% coverage). The description explains it as 'Exact path to the document or folder to delete', adding meaning beyond the schema. Examples further clarify format. While not extremely detailed, it's adequate for a single string parameter.

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 deletes documents or folders from the reMarkable tablet, which is a specific verb+resource combination. It distinguishes itself from sibling tools like remarkable_browse (browse) and remarkable_move (move).

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 warn that deletion is permanent and cannot be undone, and suggest using remarkable_browse to verify the path before deleting, providing clear when-to-use guidance and an alternative.

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 it as read-only, idempotent. Description adds detail on response formats (embedded resource vs. compatibility JSON), OCR behavior, background color defaults, and PDF/EPUB annotation-only rendering. 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?

Well-structured with <usecase>, <instructions>, <parameters>, <examples>. Slightly verbose with multiple examples but still efficient. Front-loads key info.

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 6 parameters, no output schema, and good annotations, description covers all user needs: resource fetching, OCR, background customization, and document finding via sibling tool. Complete for its 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 has zero descriptions (0% coverage). Description fully explains all 6 parameters with defaults, format details, and env var option for background. Example usage reinforces parameter semantics.

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?

Clearly states it gets an image of a specific reMarkable page. Lists specific use cases (diagrams, sketches, wireframes) and contrasts with tools like remarkable_read for 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?

Provides explicit context for use (hand-drawn content, visual context). Notes limitation for PDFs/EPUBs (only annotations rendered). Lacks explicit mention of alternatives like remarkable_read for text extraction, but context is clear.

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

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

Discloses mkdir -p behavior (auto-create intermediates) beyond annotations which only indicate non-destructive write. Lacks details on what happens if folder exists.

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?

Concise, structured with usecase, instructions, parameters, examples. Every sentence adds value.

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

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

Complete for a simple one-parameter tool with output schema. Lacks error handling details but not necessary for typical usage.

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 path is a full folder path and providing examples, adding meaning beyond the schema's type 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?

The description clearly states the verb 'create' and resource 'folder' on reMarkable tablet, distinguishing it from siblings like remarkable_delete or remarkable_upload.

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

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

Explicitly says to use for setting up folder structure before uploading, providing clear context. Does not explicitly list exclusions but sibling tools imply 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?

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the tool's non-destructive, non-read-only nature is known. The description adds some behavioral context (e.g., optional renaming) but doesn't disclose potential side effects, permissions, or error handling, stopping short of fully supplementing the 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 sections (usecase, instructions, parameters, examples) and is front-loaded with the core purpose. While efficient, the XML-like tags add minor verbosity; a plain text version could be slightly more concise.

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

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

For a simple tool with three parameters and an output schema, the description covers essential use cases, parameter roles, and examples. It lacks details on error conditions or input validation but is generally complete for typical usage scenarios.

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 and its purpose: source is 'Current path,' destination is 'New parent folder path,' and new_name is 'Optional new name.' Examples further clarify usage. However, path format conventions could be more explicit, preventing a perfect score.

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 or rename a document/folder on your reMarkable tablet,' which clearly defines the verb and resource. It distinguishes from sibling tools like remarkable_delete or remarkable_upload by indicating a non-destructive move/rename operation.

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 provide clear usage scenarios, e.g., 'To rename without moving, set destination to the current parent folder' and 'To move without renaming, omit new_name.' However, it lacks explicit guidance on when not to use this tool or direct comparison to alternatives, leaving room for improvement.

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 declare readOnlyHint=true, destructiveHint=false. The description adds behavioral context beyond annotations: pagination mechanism, content extraction types, grep filtering, OCR backend behavior, and per-parameter details. 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 well-structured with clear usecase, instructions, parameters, and examples. Front-loaded with purpose, each sentence adds value. No redundancy or waste.

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 and output schema (present but not shown), the description fully covers usage scenarios, pagination, content types, grep, OCR, and error context (via examples). It mentions the 'more' field and 'next_page' for pagination, compensating for schema gaps.

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 has 0% description coverage. The description fully explains each parameter: document (use remarkable_browse to find), content_type (enum meanings), page (default 1, notebook pages), grep (regex on current page), include_ocr (default false). Examples reinforce 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 'Read and extract text content from a reMarkable document.' It uses a specific verb and resource, distinguishing it from sibling tools like remarkable_browse (browse) and remarkable_search (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 instructions provide detailed usage guidance on pagination, content types, grep, and OCR. It implicitly differentiates from siblings but lacks explicit 'when-not-to-use' or direct alternative comparisons.

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 destructiveHint=false. The description adds behavioral details: documents are sorted newest-first, optional text preview (first ~200 chars), and the REMARKABLE_ROOT_PATH constraint. These go beyond the annotations, though the description could mention pagination or result truncation limits.

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 structured tags (<usecase>, <instructions>, <parameters>, <examples>) for clarity. Every sentence is informative and front-loaded with the use case. It is concise with no wasted words.

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

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

Given the tool's simplicity (2 optional parameters, output schema exists), the description covers all essential aspects: use case, behavior, parameter details, examples, and the REMARKABLE_ROOT_PATH note. It is complete for an AI agent to select and invoke 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?

The input schema has 0% description coverage, so the description fully compensates by clearly explaining each parameter: limit (default, max constraints) and include_preview (preview length). This adds significant semantic value beyond the schema's raw 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 clearly states the tool's purpose: 'Get your most recently modified documents.' It specifies the verb (get) and resource (recent documents) and distinguishes the tool from siblings through its focus on recentness and modification date ordering.

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 the tool ('Use this to quickly find what you were working on recently') and includes instructions on parameters and environment variable behavior. However, it does not explicitly mention when not to use it or suggest alternative tools for other scenarios.

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 provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false. The description adds behavioral context beyond these: it mentions it searches document names first, optionally grep content, returns summaries from multiple documents, and imposes limits like max 5 documents and ~8000 chars per page. 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> tags. It is concise, front-loading the use case and key limits, with no redundant sentences. Every sentence adds value, and the structure aids quick scanning.

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, 1 required, 0% schema coverage, and existence of output schema), the description is complete. It explains the return behavior (summaries from multiple documents with first page ~8000 chars), limits, parameter defaults, and examples. No gaps remain.

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. The <parameters> section explains each parameter's purpose: query for document name search, grep for content pattern, limit for max docs, include_ocr for handwritten content, tags for case-insensitive filtering. This adds meaning beyond the bare schema properties.

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 'Search[es] across multiple documents and return matching content,' specifying the verb (search) and resource (documents). It distinguishes from siblings like remarkable_read (single document) and remarkable_browse by emphasizing multi-document search with content matching.

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> tag explicitly notes efficiency for finding info across the library without many tool calls. Limits (max 5 documents, first page ~8000 chars) are clearly stated. The <examples> demonstrate usage patterns, and the parameter descriptions clarify when to use grep, tags, OCR.

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, destructiveHint, idempotentHint, openWorldHint. The description adds that it returns authentication status and diagnostic information, complementing the 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 concise with clear sections (use case, instructions, example). Every sentence adds value without 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 zero parameters, rich annotations, and an existing output schema, the description is complete. It covers purpose, usage, and provides an example.

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?

No parameters exist, so schema coverage is 100%. The description does not need to add parameter info; it correctly omits it.

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 checks connection status and authentication with reMarkable Cloud, using specific verbs and distinguishing it from sibling tools that perform other actions.

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?

Instructions say to use it for verification or troubleshooting, providing clear context. No mention of when not to use it, but the purpose is specific enough.

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

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

Annotations show readOnlyHint=false and destructiveHint=false, so the description already knows it's a non-destructive write. The description adds transparency about format restrictions and destination behavior, which complements the annotations well.

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-organized into usecase, instructions, parameters, and examples. Every sentence adds value, and the length is appropriate.

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

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

Covers formats, destination, prerequisites, and examples. Lacks mention of return value or success status, but given the output schema exists (though not shown), this is a minor 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?

With 0% schema description coverage, the description adds full value: explains file_path as 'Absolute path to local PDF or EPUB file' and destination as 'Folder path on tablet (default: "/" for root)'. This is essential for correct invocation.

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: 'Upload a PDF or EPUB file to your reMarkable tablet.' It uses a specific verb-resource combination and is distinguishable from siblings like remarkable_read 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?

Provides explicit instructions on when to use (uploading local files), format restrictions (only PDF/EPUB), and prerequisite actions (use remarkable_mkdir if destination folder doesn't exist). Includes multiple examples.

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