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

With no annotations, the description carries the full burden, and it discloses almost nothing beyond the basic action: it doesn't say whether subdirectories are traversed, whether existing files in target_dir are overwritten, whether source files are left untouched, what happens if target_dir is missing, or how failures in a batch are reported. For a bulk write operation this is a significant transparency 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?

The description is front-loaded with a one-line summary followed by a compact Args block, with no redundant prose. The docstring formatting is slightly mechanical but 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?

An output schema exists, so return-value explanation isn't required, but for a batch mutation tool with zero annotations and four parameters the description should at least cover overwrite behavior, recursion, and error handling. As written it is adequate to invoke the tool but leaves consequential side effects undocumented.

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 Args block does real work by mapping each parameter to its role and noting that source_extensions defaults to 'common formats'. However, the explanations largely restate the parameter names — target_format's accepted values (e.g. 'pdf', 'docx') and source_extensions' expected syntax are never specified.

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 first line gives a specific verb and resource ('Convert multiple documents') plus the batch scope ('in a directory') and the outcome ('to a different format'), which clearly separates it from siblings like read_document_text or merge_text_documents. It stops short of naming a sibling it is distinct from, so it isn't 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 choose this over single-document conversion, read_document_text, or search_documents, and no prerequisites (e.g. whether LibreOffice must be running). The reader must infer usage entirely from the tool name and directory-based framing.

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 full burden for behavioral disclosure. It states this creates a document but doesn't mention whether this requires write permissions, what happens if a file already exists at the path, whether the operation is atomic, or what the output contains. The description provides basic functional information but lacks important behavioral context for a creation 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?

The description is efficiently structured with a clear purpose statement followed by parameter explanations. Every sentence adds value: the first states what the tool does, and the subsequent lines explain each parameter's purpose. There's no wasted text or redundancy.

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

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

Given this is a creation tool with no annotations but with an output schema (which handles return values), the description is moderately complete. It explains the parameters well but lacks behavioral context about permissions, file overwriting, or error conditions. The presence of an output schema means the description doesn't need to explain return values, but for a mutation tool, more behavioral guidance would be helpful.

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 well by explaining all three parameters: 'path' (full path where document should be created), 'doc_type' (type with specific options listed), and 'content' (initial content for writer documents). It adds meaningful context beyond the bare schema, though it could clarify that 'content' only applies to 'writer' type documents.

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 'new LibreOffice document', making the purpose immediately understandable. It distinguishes from siblings like 'open_document_in_libreoffice' or 'read_document_text' by focusing on creation rather than opening or reading existing documents. However, it doesn't explicitly differentiate from 'create_live_editing_session' which also creates something.

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 no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, when not to use it, or comparison to sibling tools like 'create_live_editing_session' or 'open_document_in_libreoffice'. The agent must infer usage from the tool 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'automatic refresh capabilities' but doesn't explain what this entails, such as how often refreshes occur or what triggers them. Critical details like permissions required, whether the session is persistent, or potential side effects are missing, leaving significant gaps in understanding the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, with a clear purpose statement followed by a brief parameter list. Each sentence serves a purpose, and there's no unnecessary verbosity, making it easy to scan and understand quickly.

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 (creating a live editing session) and the presence of an output schema, the description is moderately complete. It covers the basic purpose and parameters but lacks details on behavioral aspects like session management or refresh behavior. The output schema likely handles return values, so the description doesn't need to explain those, but it should provide more context on usage and limitations.

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 description adds minimal semantics beyond the input schema, which has 0% coverage. It briefly explains 'path' as 'Path to the document for live editing' and 'auto_refresh' as 'Whether to enable automatic refresh detection', but this doesn't fully compensate for the lack of schema descriptions. For example, it doesn't specify the format of 'path' or what 'automatic refresh detection' means in practice, leaving parameters partially unclear.

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

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

The description clearly states the action ('Create a live editing session') and the resource ('document for live editing'), specifying the tool's purpose. However, it doesn't distinguish this tool from potential siblings like 'create_document' or 'watch_document_changes', which might involve similar document operations but with different functionalities.

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 is provided on when to use this tool versus alternatives. The description lacks context about prerequisites, such as whether the document must exist or be accessible, and doesn't mention any sibling tools like 'create_document' or 'watch_document_changes' that might serve overlapping purposes.

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 so well: it explains why the check exists (LO Bug 32419 ignores m:r/w:rPr/w:sz, so formula font size and overflow judgments are distorted), which tells the agent the practical consequence of a false negative. It omits error behavior for missing/non-docx paths and whether the check is cheap or does full XML parsing.

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 opening line, followed by the rationale and the routing rule. The dated changelog framing ('2026-10-24') and bug number are slightly noisy, but each sentence supports the routing decision 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?

For a one-parameter boolean predicate with an output schema, the description supplies enough: what is checked, why it matters, and what to do with each outcome. Only edge-case behavior (invalid path, non-docx input, relative vs absolute paths) is left unspecified.

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 single parameter has 0% schema description coverage — the schema only supplies type string with format path. The description implies the path targets a docx but never states whether it must be an absolute local path, a workspace-relative path, or what happens for non-.docx files, so the gap is only partially compensated.

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 first sentence states a specific verb and resource: detect whether a docx contains OMML formulas, and even names the exact XML location checked (word/document.xml, <m:oMath>). This is a narrow predicate tool, and its scope is unambiguous relative to conversion or text-reading 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?

The description gives explicit branching guidance: formulas present → route to Word COM for true rendering; absent → use LibreOffice as usual for speed. That is a clear use/no-use decision. It stops short of naming the sibling tools (batch_convert_documents, open_document_in_libreoffice) that the routing decision feeds into.

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 of behavioral disclosure. It states the tool gets 'detailed information' but doesn't specify what that includes (e.g., metadata, structure, content), whether it's read-only, or any performance or permission considerations. This leaves significant gaps for a tool with no 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?

The description is appropriately sized with two sentences: a purpose statement and a parameter explanation. It's front-loaded with the main function, though the 'Args' section could be integrated more smoothly. Overall, it avoids 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?

Given the tool has an output schema (which handles return values), no annotations, and a simple parameter structure, the description is minimally adequate. It covers the basic purpose and parameter, but lacks usage guidance and behavioral details, making it incomplete for optimal agent understanding in a context with many 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?

The description includes an 'Args' section that documents the single parameter 'path', adding meaning beyond the input schema which has 0% description coverage. However, it only states 'Path to the document file' without clarifying format (e.g., absolute/relative, file extensions) or constraints, providing basic but incomplete compensation for the schema 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?

The description clearly states the verb 'Get' and resource 'detailed information about a LibreOffice document', making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_document_statistics' or 'read_document_text', which appear to serve similar informational purposes.

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 is provided on when to use this tool versus alternatives. With siblings like 'get_document_statistics' and 'read_document_text' available, the description lacks any indication of what distinguishes this tool or when it should be preferred over 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'Get[s] detailed statistics' but doesn't specify what types of statistics (e.g., word count, page count, file size), whether it's read-only or has side effects, or any performance or permission considerations. This leaves significant gaps for a tool that likely interacts with documents.

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 appropriately sized and front-loaded, with the core purpose stated first in a clear sentence. The additional 'Args' section is concise and relevant, though it could be integrated more smoothly. There's no wasted text, making it efficient for quick understanding.

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 (single parameter, no annotations, but with an output schema), the description is minimally adequate. The output schema likely covers return values, reducing the need for detailed output explanations. However, it lacks context on statistics types, usage distinctions from siblings, and behavioral traits, leaving room for improvement in guiding the agent effectively.

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 description adds minimal semantics beyond the input schema, which has 0% description coverage. It mentions 'path: Path to the document file', clarifying the parameter's purpose, but doesn't provide format details (e.g., absolute vs. relative paths, supported file types) or examples. With one parameter and low schema coverage, this offers some compensation but remains basic.

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 with a specific verb ('Get') and resource ('detailed statistics about a document'), making it immediately understandable. However, it doesn't explicitly distinguish this tool from sibling tools like 'get_document_info' or 'read_document_text', which might provide overlapping or related functionality, preventing a perfect score.

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 no guidance on when to use this tool versus alternatives. With siblings like 'get_document_info' and 'read_document_text' available, there's no indication of what makes 'get_document_statistics' unique or appropriate for specific scenarios, leaving the agent to guess based on tool names 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 provided, the description carries full burden but only minimally addresses behavior. It mentions 'insert' implies mutation but doesn't disclose critical traits like whether changes are saved automatically, permission requirements, error handling, or side effects on document formatting. This leaves significant gaps for a mutation 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?

The description is efficiently structured with a clear purpose statement followed by a bullet-point list of parameters. Every sentence earns its place without redundancy, making it easy to scan and understand quickly.

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 a mutation tool with no annotations, 3 parameters, and an output schema (which reduces need to describe returns), the description is minimally adequate. It covers the basics but lacks depth on behavioral context, error conditions, and integration with sibling tools, leaving room for improvement.

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. It lists all three parameters with brief explanations, adding value beyond the bare schema. However, it doesn't elaborate on format details (e.g., path syntax, text encoding, position enum meanings beyond listing them), keeping it at a baseline level.

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 ('Insert text') and resource ('into a LibreOffice Writer document'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'merge_text_documents' or 'create_document', which prevents a perfect score.

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 no guidance on when to use this tool versus alternatives like 'create_document' or 'merge_text_documents'. It lacks context about prerequisites (e.g., document must exist) or exclusions, offering only basic parameter explanations without usage 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that documents are merged and saved, implying a write operation, but lacks details on permissions, error handling, file format support, or what happens if output_path exists. This is insufficient for a mutation 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?

The description is front-loaded with the core purpose in the first sentence, followed by a structured Args section that efficiently documents parameters without redundancy. Every sentence serves a clear purpose, making it appropriately sized and easy to parse.

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 (3 parameters, mutation operation) and the presence of an output schema (which handles return values), the description covers the basic operation and parameters. However, it lacks behavioral context like file handling or error scenarios, making it adequate but incomplete for safe 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?

Schema description coverage is 0%, so the description must compensate. It lists all three parameters (document_paths, output_path, separator) with brief explanations, adding meaning beyond the schema's titles. However, it doesn't specify path formats or separator usage details, leaving some gaps in semantic clarity.

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 action ('Merge multiple text documents') and the resource ('into a single document'), distinguishing it from siblings like 'batch_convert_documents' or 'create_document' which involve different operations. It directly answers what the tool does without being vague or tautological.

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 no guidance on when to use this tool versus alternatives like 'create_document' or 'insert_text_at_position', nor does it mention prerequisites or exclusions. It states what the tool does but offers no context for selection among the available document manipulation tools.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool opens a document in LibreOffice GUI for live viewing, which implies a user interface interaction and potential resource usage. However, it doesn't mention behavioral traits like whether it launches a new instance, handles errors for invalid paths, or requires LibreOffice installation, leaving gaps in understanding the tool's 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?

The description is front-loaded with the core purpose in the first sentence, followed by a structured 'Args:' section that efficiently documents parameters. Every sentence adds value without redundancy, making it appropriately sized and easy to parse quickly.

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 (2 parameters, no annotations, but has an output schema), the description is mostly complete. It covers the purpose and parameters adequately, but since an output schema exists, it doesn't need to explain return values. However, it could benefit from more behavioral context, such as error handling or prerequisites, to be fully comprehensive.

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. It adds meaning by explaining 'path' as 'Path to the document to open' and 'readonly' as 'Whether to open in read-only mode (default: False)', which clarifies the purpose and default behavior beyond the bare schema. However, it doesn't detail path format constraints or read-only implications, keeping it from 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 clearly states the specific action ('Open a document in LibreOffice GUI for live viewing'), identifies the resource ('document'), and distinguishes it from siblings like 'create_document' or 'read_document_text' by emphasizing GUI interaction and live viewing. It provides a verb+resource combination that is precise and unambiguous.

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

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

The description implies usage for opening documents in LibreOffice GUI, which suggests it's for interactive viewing rather than batch processing or conversion (contrasted with siblings like 'batch_convert_documents' or 'convert_document'). However, it lacks explicit guidance on when not to use it or direct alternatives, such as 'refresh_document_in_libreoffice' for already open documents.

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 full burden but only states the basic action. It doesn't disclose behavioral traits like error handling (e.g., for invalid paths or unsupported formats), performance aspects (e.g., large file handling), or output specifics (though an output schema exists). This leaves gaps in understanding the tool's operation beyond its core function.

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 appropriately sized with two sentences: one stating the purpose and another listing the parameter. It's front-loaded with the main action, though the parameter section is brief. There's no wasted text, making it efficient for a simple 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 low complexity (one parameter) and the presence of an output schema, the description is minimally complete. However, it lacks details on error cases, file format support, or integration with sibling tools, which could aid an agent in correct invocation. It meets basic needs but leaves room for improvement in contextual 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?

The description adds minimal semantics beyond the input schema, which has 0% coverage. It only repeats the parameter name 'path' without explaining format (e.g., absolute vs. relative), constraints, or examples. With one parameter and low schema coverage, the description provides basic context but doesn't fully compensate for the lack of detailed documentation.

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 'extract' and resource 'text content from a LibreOffice document', making the purpose specific and understandable. It distinguishes from siblings like 'read_spreadsheet_data' by specifying document text extraction, though it doesn't explicitly differentiate from 'get_document_info' or 'get_document_statistics'.

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 no guidance on when to use this tool versus alternatives like 'get_document_info' (which might include metadata) or 'read_spreadsheet_data' (for spreadsheet content). It lacks context about prerequisites, such as file accessibility or format support, offering only basic usage without exclusions or 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?

With no annotations provided, the description carries the full burden and does well: it discloses the non-obvious three-layer z-order model (masters < layouts < slide shapes), warns that overlap judgments must merge all three layers because decorative blocks live on layouts/masters, and explains that geometry of None means the value is not explicitly set and is inherited from a layout placeholder. It does not cover performance on large decks or how images/charts are represented, which is why it falls short of 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?

The description is front-loaded with the core capability before the z-order nuance and the sibling comparison, and every claim carries practical weight. The z-order section is slightly verbose, but it encodes information an agent could not infer otherwise, so it largely 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?

Return format does not need explaining because an output schema exists. Combined with explicit format restrictions, the usage scenario, the inheritance caveat, and the routing to convert_document, an agent has everything it needs in order to call this tool correctly and to know when not to.

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: path is identified as the .pptx path, and slides is documented as an optional page filter with concrete syntax examples ("1", "1,3-5") and a stated default of reading all pages. Minor gap: path is not described in terms of relative vs absolute paths or error behavior for a missing or non-.pptx file.

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 (精确读取) and a precisely scoped resource: the per-element geometry for each slide of a .pptx file, enumerated as coordinates, size in cm, rotation, placeholder role, z-order, group children, and text summary. It then explicitly sets itself apart from read_document_text by saying that one only returns a text stream and loses all position data.

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 states the exact questions this tool answers (where an element sits, how large it is, whether it overlaps or exceeds bounds, and which element covers which), names the competing sibling read_document_text and why that sibling is insufficient, and gives an explicit fallback path: convert .ppt/.odp to pptx with convert_document first. The exclusions are unambiguous.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes a read operation with parameters but lacks details on permissions, file access requirements, error handling, or output format. While it implies a non-destructive read, it does not explicitly state safety aspects like whether it modifies the file or has rate limits, leaving significant gaps for a tool with no 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?

The description is front-loaded with the core purpose, followed by a structured list of parameters with clear explanations. Every sentence adds value without redundancy, and the format is efficient for quick comprehension, making it appropriately sized for the tool's complexity.

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, the description does not need to explain return values. However, with no annotations and 0% schema description coverage, it partially compensates with parameter semantics but lacks behavioral context like error cases or performance limits. It is adequate for a read operation but has clear gaps in safety and usage 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?

The schema description coverage is 0%, so the description must compensate. It adds meaningful semantics for all three parameters: path specifies file types (.ods, .xlsx), sheet_name clarifies behavior when None (reads first sheet), and max_rows defines a default (100). This goes beyond the bare schema, though it could provide more context on path validation or max_rows 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?

The description clearly states the specific action ('Read data from') and resource ('LibreOffice Calc spreadsheet'), distinguishing it from sibling tools like read_document_text or get_document_info that handle different document types or operations. It precisely defines what the tool does without being vague or tautological.

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 no guidance on when to use this tool versus alternatives like read_document_text (for text documents) or get_document_info (for metadata). It mentions default behavior for sheet_name and max_rows but does not specify use cases, prerequisites, or exclusions, leaving the agent to infer usage from context 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 burden of behavioral disclosure. It mentions 'refresh signal' and 'reload a document', implying a read-only or update operation, but fails to detail critical aspects like whether this requires LibreOffice to be running, if it affects unsaved changes, error handling, or response behavior. This leaves significant gaps for a tool interacting with external software.

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 brief and front-loaded with the main purpose in the first sentence, followed by parameter details. It avoids unnecessary words, though the structure could be slightly improved by integrating the parameter explanation more seamlessly.

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 (interacting with LibreOffice), lack of annotations, and presence of an output schema (which reduces need to explain returns), the description is minimally adequate. It covers the basic action and parameter but misses important contextual details like dependencies on LibreOffice state or error scenarios, making it incomplete for safe use.

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 description adds meaningful context for the single parameter 'path' by specifying it as 'Path to the document that should be refreshed', which clarifies its role beyond the schema's basic type. With 0% schema description coverage and only one parameter, this compensates adequately, though it could include format examples (e.g., file paths).

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

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

The description clearly states the action ('Send a refresh signal') and the resource ('to LibreOffice to reload a document'), making the purpose specific and understandable. However, it does not explicitly differentiate from sibling tools like 'open_document_in_libreoffice' or 'watch_document_changes', which might involve similar document-handling operations.

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 no guidance on when to use this tool versus alternatives. It lacks context such as prerequisites (e.g., document must be open in LibreOffice), exclusions, or comparisons to siblings like 'open_document_in_libreoffice' for initial loading or 'watch_document_changes' for monitoring updates.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the search functionality but doesn't describe what 'search' entails—whether it's case-sensitive, supports regex, returns partial matches, or includes metadata in results. It also omits performance characteristics like speed, rate limits, or error conditions, which are critical for a search 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?

The description is appropriately sized and front-loaded, with the core purpose in the first sentence and parameter details following. There's no wasted text, but the structure could be slightly improved by integrating parameter explanations more seamlessly rather than a separate 'Args:' section, though this is minor.

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 (2 parameters, no annotations, but with an output schema), the description is minimally adequate. The output schema likely covers return values, reducing the need for result explanation. However, for a search tool, it should better address behavioral aspects like search scope and limitations, which are missing, making it incomplete for optimal agent use.

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. It adds basic semantics for both parameters: 'query' as 'Text to search for' and 'search_path' with a default and scope hint ('common document locations'). This clarifies intent beyond the bare schema, but lacks details like format examples, path validation rules, or query syntax, leaving gaps in practical 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 the tool's purpose with a specific verb ('Search') and resource ('documents'), and specifies the search criteria ('containing specific text'). It distinguishes itself from siblings like 'read_document_text' or 'get_document_info' by focusing on text-based search rather than direct reading or metadata retrieval. However, it doesn't explicitly differentiate from potential overlapping tools like 'watch_document_changes' in terms of search scope.

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 no guidance on when to use this tool versus alternatives. It doesn't mention when to prefer this over 'read_document_text' for content extraction or 'get_document_info' for metadata-based filtering. There's no context about prerequisites, limitations, or typical use cases, leaving the agent to infer usage from the purpose 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 provided, the description carries the full burden of behavioral disclosure. It mentions 'live updates' and a duration, but lacks details on how updates are delivered (e.g., streaming, polling), what constitutes a 'change', permissions required, rate limits, or whether it's a blocking call. This is inadequate for a tool that likely involves real-time monitoring.

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 appropriately sized and front-loaded, with the core purpose stated first. The parameter explanations are brief and directly relevant. However, the 'Args:' section could be integrated more seamlessly, and some sentences might benefit from additional context to enhance clarity without adding bulk.

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 (real-time monitoring) and lack of annotations, the description is minimally adequate. It covers the basic action and parameters but misses behavioral details like update mechanisms or error handling. The presence of an output schema helps, but the description doesn't reference it, leaving gaps in understanding the full tool behavior.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaningful context for both parameters: 'path' is explained as 'Path to the document to watch', and 'duration_seconds' as 'How long to watch for changes (default: 30 seconds)'. This clarifies their roles beyond the bare schema, though it doesn't detail path formats or duration 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?

The description clearly states the tool's purpose: 'Watch a document for changes and provide live updates.' It specifies the verb ('watch'), resource ('document'), and outcome ('live updates'), making it easy to understand. However, it doesn't explicitly differentiate from siblings like 'get_document_info' or 'refresh_document_in_libreoffice', which might also involve document monitoring or updates.

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 no guidance on when to use this tool versus alternatives. It mentions the action but doesn't specify scenarios (e.g., for real-time collaboration vs. static analysis) or compare it to siblings like 'create_live_editing_session' or 'refresh_document_in_libreoffice', leaving the agent to infer usage from context alone.

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