Mila

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

No annotations are provided, so the description carries the full burden. It discloses the append action and the parameter modes, but it does not mention return values, error behavior, or permission requirements. The term 'append' implies non-destructive modification, but this remains implicit.

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

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

The description is a single, focused sentence with a short clarifying clause. It front-loads the primary purpose and gives just enough detail about parameter usage without unnecessary elaboration.

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 append tool, the description covers the essential context: what it does, the target resource, and the key parameter selection guidance. It lacks details about return values or error handling, but the absence of an output schema and the tool's straightforward nature make this acceptable.

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

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

The input schema already describes all four parameters with 100% coverage, earning a baseline of 3. The description adds value by explicitly distinguishing the purposes of 'rows' (multiple rows) and 'values' (single row), which is not immediately clear from the schema alone.

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 ('Append') and the target resource ('spreadsheet tab'), which distinguishes it from sibling tools like append_slides and append_to_document. It also further clarifies by describing the two modes of operation (multiple rows vs. single value).

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 context: the tool is for appending data to a spreadsheet tab, and it gives a clear decision rule for when to use 'rows' versus 'values'. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of a full 5.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the basic action and does not mention whether existing slides are affected, how position is handled, permission requirements, return values, or the non-destructive nature of appending. Significant behavioral context is missing.

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

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

The description is a single, front-loaded sentence that efficiently states the action and resource. Parenthetical synonyms add helpful context without unnecessary verbosity. Every word earns its place.

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

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

With 4 parameters, nested objects, no output schema, and no annotations, the description is far too minimal. It does not explain how to choose between slide vs slides, the semantics of the position parameter, what the function returns/doesn't return, or any edge cases. The description is inadequate for a tool with this complexity.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds minimal semantic value beyond the schema, merely restating that one or more slides can be appended. It does not clarify the distinction between using 'slide' vs 'slides' or the position parameter's behavior.

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

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

The description clearly states the tool appends slides to an existing presentation, with a specific verb (append) and resource (slides/presentation). It distinguishes from sibling tools like create_slide_presentation by emphasizing 'existing,' making the purpose 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 adding slides to an existing presentation, but provides no explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives like create_slide_presentation for new presentations or update_slide_presentation for modifying existing slides. The context is inferred rather than stated.

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

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

With no annotations, the description carries the full burden. It discloses the core behavior (append, non-destructive) and adds context about supported document types ('doc, word, note') and content format (HTML). However, it lacks details on error handling, permissions, or what happens if the document does not exist.

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

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

The description is a single, focused sentence that front-loads the action and includes necessary qualifiers without any redundancy or filler. Every word contributes 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?

For a simple two-parameter tool with no output schema and no annotations, the description is largely complete. It communicates the main action, content format, and safety guarantee. It could be enhanced by mentioning behavior when the document is not found, but this is a minor gap given the low 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?

The input schema provides complete descriptions for both parameters (100% coverage), so the baseline is 3. The description adds minimal extra meaning beyond noting that content is HTML, which is already in the schema. The parameter semantics are adequately served by 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 clearly states the action (append), the target (existing document), and the content type (HTML). It distinguishes itself from siblings by explicitly noting 'without replacing existing content,' which separates it from update_document and create_document.

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: to add content to an existing document. It implicitly suggests use over update_document by noting no replacement, but it does not explicitly name alternatives or exclusion criteria.

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

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

There are no annotations, so the description carries the behavioral disclosure burden. It adds the important requirement that 'Content should be HTML (e.g. "<p>Hello</p>")' and gives a simple example. However, it doesn't disclose other behavioral traits such as whether the document is created in a specific location, what happens on success, or any side effects beyond creation.

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

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

The description is two sentences long, front-loaded with the core purpose, and every word earns its place. It efficiently packs the action, trigger phrases, and content format guidance 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?

For a simple create operation with no output schema and no annotations, the description provides sufficient context: it states the action, when to use it, and the content format. It could be improved by briefly noting what a successful response looks like or mentioning the optional nature of server_id, but these are covered by the schema and the description is generally complete for the tool's simplicity.

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

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

All three parameters are described in the schema (100% coverage), so the baseline is 3. The description adds value by specifying the format for the 'content' parameter ('should be HTML' with an example), which the schema only describes as 'HTML content of the document.' This enhances parameter understanding.

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 'Create a new document,' which is a specific verb+resource pair. It further clarifies scope with a list of user intents ('create, write, draft, or compose a document, doc, note, page, article, or word document') which clearly differentiates it from sibling tools for spreadsheets and slide decks.

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 states when to use the tool: 'Use this when asked to create, write, draft, or compose a document...' This gives clear context. However, it doesn't mention explicit exclusions like 'do not use for spreadsheets or slides,' so it misses full 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?

With no annotations, the description carries the full burden but only adds minimal behavioral context ('with an initial tab', 'organize data in rows and columns'). It does not disclose side effects (e.g., whether it overwrites existing sheets), permission requirements, or response 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 two concise sentences: the first states what the tool does, the second gives usage guidance. No redundancy or unnecessary detail.

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 creation tool with a rich schema, the description covers core purpose and use cases, but it omits what the response will contain (e.g., spreadsheet ID, URL). Since there is no output schema, this missing information makes the description incomplete.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The tool description adds little beyond that, offering contextual background but no parameter-specific details, so it stays at the baseline of 3.

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 'Create a new spreadsheet' with synonyms and concrete use cases ('table, workbook, tracker, or organize data in rows and columns'). It effectively distinguishes this tool from siblings like create_document, create_slide_presentation, and create_sheet_tab.

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 provides when to use the tool ('Use this when asked to create a spreadsheet, table, workbook, tracker...'), giving clear context. However, it does not mention when not to use it or suggest alternatives, which would be helpful given the 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?

No annotations are provided, so the description must disclose behavioral traits, but it does not. It omits important details such as whether the spreadsheet must already exist, what happens if the tab name is duplicate, or any side effects. The description simply states 'Add a new tab' without revealing constraints or outcomes.

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

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

The description is a single sentence that is direct and front-loaded. It wastes no words and immediately communicates the core action. The parenthetical clarification is short and harmless. It is an example of concise, purposeful writing.

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 5 parameters (including a nested object for cells), no annotations, and no output schema, the description is too sparse to be contextually complete. It lacks guidance on preconditions, return values, or how the complex 'cells' parameter integrates. The schema covers parameter syntax, but the description does not fill the contextual gaps an agent needs.

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 has 100% coverage with descriptions for all parameters, so the baseline is 3. The tool description adds no information about parameters; it merely repeats the concept of adding a tab. Since the schema already documents each parameter well, the description does not need to compensate, but it also provides no extra semantic value.

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

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

The description uses a specific verb and resource: 'Add a new tab to a spreadsheet.' It clearly distinguishes this from create_sheet (which creates a whole spreadsheet) and other sibling tools like update_sheet_tab or delete_sheet_tab. The parenthesis '(sheet, excel, workbook)' clarifies the general meaning of spreadsheet, adding no confusion.

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 given about when to use this tool versus alternatives. There is no mention of prerequisites (e.g., needing an existing spreadsheet ID) or exclusions. The description merely states the action, leaving the agent to infer usage context from the tool name and schema.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It explains that each slide has 'html' content and optional 'background' and 'notes', which is useful data-structure context. However, it omits details about side effects, required permissions, or the response format (e.g., whether an ID is returned), leaving significant behavioral ambiguity for a create 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 three sentences, each earning its place. The first sentence states the core action, the second clarifies when to use it, and the third explains the slide object structure. No redundant words or filler.

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

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

The tool has 5 parameters, no output schema, and no annotations. The description covers the main purpose and slide data structure, which is helpful. However, it fails to mention what the tool returns (e.g., a presentation ID or URL), which is critical for an agent to reference the created presentation later. Given the moderate complexity, the description is adequate but not complete.

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

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

The schema has 100% parameter description coverage, so the baseline is 3. The description adds some meaning by explaining the slide structure (html, background, notes) which aligns with the schema's items, but it does not go beyond the schema to clarify relationships or provide additional syntax hints. It neither improves nor harms parameter understanding.

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

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

The description opens with a specific verb and resource: 'Create a new slide presentation'. It also lists synonyms (slides, powerpoint, deck, keynote) and clearly distinguishes from sibling creation tools like create_document and create_sheet by focusing on presentations. The purpose is unambiguous.

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

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

The description states 'Use this when asked to create a presentation, slide deck, or slideshow', giving explicit context for when the tool is appropriate. However, it does not mention alternatives, such as append_slides for adding slides to an existing presentation, so it stops short of full when-not/alternatives 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?

The description explicitly warns that deletion is permanent, which is the most critical behavioral trait for a destructive operation. However, with no annotations, it does not mention authorization requirements, idempotency, side effects, or error behavior, leaving meaningful gaps.

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

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

The description is a single sentence with no filler. It efficiently states the action, object type, and required input.

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 deletion tool, the description adequately covers the action, object, and input mechanism. It omits return behavior and error cases, but given low complexity and fully documented schema, it is sufficiently complete.

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

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

Schema coverage is 100%: the single required id is already documented as 'Document ID.' The description repeats 'by ID' and expands 'document' to doc/word/note, but adds no semantic detail beyond what the schema already 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 uses the specific verb 'Permanently delete' and clearly identifies the resource as a document (doc, word, note) by ID. This distinguishes it from sibling delete_sheet and delete_slide_presentation tools.

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

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

The description implies it is for documents, not sheets or slides, and requires an ID. It does not explicitly mention alternatives or exclusions, but the sibling tool names make the scope 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?

With no annotations, the description carries the burden of disclosing behavior. It explicitly states the action is permanent and cascades to all tabs, which are critical behavioral traits. It does not mention potential side effects (e.g., permissions or linked data), but the core irreversible nature is clearly conveyed.

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

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

The description is a single, front-loaded sentence of 13 words. Every word earns its place, conveying the verb, resource, and scope 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 the tool's simplicity (1 param, no output schema), the description adequately covers the purpose and key behavior. While it does not detail return values or error responses, the absence of an output schema reduces the need for such detail, and the description is sufficient for a delete operation.

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

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

The input schema already describes the single parameter 'id' as 'Sheet (workbook) ID' with 100% coverage. The description adds a small clarification by equating 'spreadsheet', 'excel', and 'workbook', but does not provide additional parameter syntax or format details, so the baseline of 3 is appropriate.

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

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

The description clearly states the action ('Permanently delete') and the resource ('a spreadsheet (sheet, excel, workbook)') with explicit scope ('and all its tabs'). This distinguishes it from sibling tools like delete_sheet_tab, which targets an individual tab.

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 deleting entire workbooks, and the sibling tool delete_sheet_tab provides an obvious alternative for deleting only a tab. However, it does not explicitly state when to use this tool versus alternatives or mention any prerequisites.

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 a key behavioral rule (last tab cannot be deleted) but does not mention permanence, permissions, or error behavior for a destructive operation. Some context is provided, but more could be added.

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

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

The description is a single, well-structured sentence that is front-loaded with the main action and includes a valuable constraint. Every word earns its place with no redundancy.

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

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

For a simple tool with two well-described parameters and no output schema, the description is nearly complete. It covers the core action and a critical edge case. Minor gaps like irreversibility and permission requirements are present but not essential for basic 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 100%, so the baseline is 3. The description adds no additional parameter context beyond what the schema already provides for tab_id and sheet_id, and does not explain relationships or formats.

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 deletes a tab from a spreadsheet, with a specific verb and resource. It also clarifies terminology (sheet, excel, workbook) and is distinct from sibling delete_sheet, which deletes the entire sheet.

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 a clear usage constraint ('Cannot delete the last remaining tab') but does not explicitly mention alternatives or when to use this tool versus delete_sheet or update_sheet_tab. The user must infer from the name and sibling list.

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

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

With no annotations, the description must disclose behavioral traits. It appropriately discloses the permanent/destructive nature of the operation. However, it lacks details on required permissions, error conditions, or side effects, which would be valuable for a mutation tool, so transparency is moderate.

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

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

The description is a single, focused sentence that front-loads the key information ('Permanently delete') and uses parentheses to clarify the resource. No wasted words; it is efficiently 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 one-parameter delete tool, the description plus schema covers the essential invocation details. It lacks information about error handling or return behavior, but given the tool's simplicity, this is a minor gap, making it adequately complete.

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

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

The input schema already fully describes the single 'id' parameter as 'Presentation ID' (100% coverage). The description adds no parameter-specific meaning beyond the schema, so it stays at the baseline score of 3.

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 identifies the action ('Permanently delete') and the resource ('slide presentation'), with synonyms to disambiguate. It distinguishes from sibling delete tools like delete_document and delete_sheet by specifying the resource type, achieving a specific and unique 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 description implies usage based on resource type but does not explicitly state when to use this tool versus alternatives. It doesn't mention exclusions or alternative tools, so the guidance is only implicit from the tool name and parenthetical.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It reveals what is returned (full content: title, HTML body, metadata), which adds context beyond the schema. However, it doesn't mention any potential caveats like authentication requirements or error behavior, though 'Get' implies a read-only 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?

A single, focused sentence that front-loads the action ('Get') and resource ('document'), then enumerates contents. No filler or redundant information; every word earns its place.

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

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

The tool is a simple one-parameter getter with a fully-described schema. The description covers the purpose, input semantics (by ID), and the complete return content. There is no output schema to explain, and the description is sufficient for a tool of this complexity.

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

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

Schema coverage is 100%: the only parameter 'id' is described as 'Document ID'. The description's phrase 'by ID' confirms this but adds no additional meaning beyond what the schema already provides, so the baseline score of 3 applies.

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

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

The description clearly states 'Get a document (doc, word, note, page) by ID' with a specific verb and resource type, and lists the contained content (title, HTML body, metadata). This distinguishes it from sibling getters like get_sheet and get_slide_presentation, which target different resource types.

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 is clear when to use this tool: to retrieve a single document's full content by ID. It implies a contrast with list_documents (for listing) and other getters for different resource types, though it doesn't explicitly state exclusions or alternatives. The mention of 'doc, word, note, page' provides context on applicability.

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 transparency burden. It discloses that the response includes all tabs and cell data in A1 notation, and 'get' implies a read operation. However, it doesn't mention permissions, rate limits, or potential large-sheet implications, leaving gaps.

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

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

The description is a single, well-structured sentence that front-loads the core action ('Get a spreadsheet by ID') and specifies the return scope without any 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?

For a simple tool with one required parameter and no output schema, the description adequately covers the key behavior and return value (all tabs, A1 notation). It could be improved by noting possible performance or pagination for large sheets, but it's sufficient for basic 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 schema already provides 100% coverage for the 'id' parameter with the description 'Sheet (workbook) ID.' The tool description only reiterates 'by ID' without adding new details about format or usage, so the baseline of 3 applies.

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

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

The description clearly states the tool gets a spreadsheet by ID and specifies the included content (all tabs, cell data in A1 notation). This distinguishes it from siblings like get_sheet_tab (for a single tab) and list_sheets (for 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 implies the tool provides full workbook contents, so an agent can infer that get_sheet_tab is for individual tabs. However, it doesn't explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

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

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

No annotations are present, so the description carries the transparency burden. It clearly implies a read-only operation with 'Get' and discloses that the result includes all cell data in A1 notation. However, it does not mention potential errors, authorization requirements, or the response structure beyond the A1 notation detail.

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

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

The description is a single, focused sentence that leads with the action and resource, followed by a valuable detail about the data format. No redundant words or filler.

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

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

With no output schema, the description partially explains the return by noting it includes all cell data in A1 notation, but leaves the exact response structure ambiguous. The tool is simple and parameters are fully documented, but missing guidance on when to use it and exact return shape reduces 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?

The input schema already documents both parameters with descriptions ('Tab ID' and 'Sheet (workbook) ID'). The description adds context by clarifying that the sheet is a workbook and the tab is the specific sheet within it, but does not add further parameter-level detail such as format or 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 uses the specific verb 'Get' and clearly specifies the resource: 'a single tab from a spreadsheet'. It adds detail about the return data ('all cell data in A1 notation') and includes terminology disambiguation ('sheet, excel, workbook') which helps differentiate it from sibling tools like get_sheet.

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 does not mention that get_sheet might be for whole workbooks or that list_sheets is for discovery. No exclusions or alternative references are provided.

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 transparency burden. It adds the behavioral detail that the response includes 'all slide data', which is useful, but it does not disclose other traits such as authentication requirements, potential response size, or error behavior. This is adequate but not rich.

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

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

The description is a single concise sentence, front-loaded with the verb and resource, and adds synonym context without unnecessary fluff. Every word earns its place, making it efficient 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?

For a simple get-by-ID tool with one parameter and no output schema, the description is largely complete: it states the action, the resource, the identifier, and that slide data is included. However, without an output schema, a bit more detail about the response structure could be beneficial, but it is not a critical 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?

The input schema fully documents the single 'id' parameter with a clear description ('Presentation ID'), giving 100% schema coverage. The tool description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool retrieves a slide presentation by ID, with a specific verb ('get') and resource ('slide presentation') plus synonyms to disambiguate. It distinguishes itself from sibling tools like get_document and get_sheet by explicitly targeting presentations, and from list_slides by indicating it fetches a single presentation including its slide 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?

The description implies usage when you have a presentation ID, but does not explicitly mention when to use this tool over alternatives such as list_slides or get_document. There are no exclusions or comparative guidance, leaving the appropriate context for the agent to infer.

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 transparency burden. It discloses that the tool lists all documents and supports pagination, sorting, and filtering by workspace, which are useful behavioral details. However, it does not mention side effects, return format, or error scenarios, leaving some gaps.

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

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

The description is two sentences, front-loaded with the core action ('List all documents'), and every sentence provides useful context. No redundancy or filler.

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

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

For a simple list tool with a rich schema and no output schema, the description is mostly complete. It covers what documents are included, when to use it, and key capabilities. It could be slightly more explicit about return behavior, but given the tool's simplicity, this is sufficient.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds the term 'workspace' as a semantic link to server_id and mentions pagination/sorting, but it does not explain parameter formats or constraints beyond what the schema already 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 uses a specific verb ('List') and resource ('documents') with synonyms (docs, word, notes, pages) to clarify scope. It clearly distinguishes from sibling tools like list_sheets or list_slides by naming the document resource type.

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

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

Explicitly states when to use: 'when asked to list, find, or search documents, notes, drafts, or written content.' It does not mention when-not or alternatives, but sibling tools cover other resource types, so the contextual guidance 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?

No annotations are provided, so the description carries the burden. 'List' implies read-only behavior, and the scope 'you have access to' adds context about visibility. It doesn't mention pagination or response format, but for a simple list operation the core safety profile is clear.

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

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

The description is a single, front-loaded sentence with no waste. It quickly communicates the action, the resource, and the scope.

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 listing tool with no parameters and no output schema, the description is adequate. It states what is listed and the access boundary. It could explain return structure, but for a list operation the intent is clear.

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

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

The tool has zero parameters and the schema is empty, so there are no parameter details to explain. The baseline score of 4 applies because no parameter descriptions are necessary.

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 'List all workspaces (servers) you have access to' with a specific verb and resource. It distinguishes itself from sibling tools that list documents, sheets, or slide presentations by explicitly referring to servers/workspaces.

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: use this tool when you need to retrieve the set of workspaces/servers available to you. While it doesn't explicitly name alternatives, the resource type is distinct from siblings, making when-to-use obvious.

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

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

No annotations are provided, so the description carries the burden. It adds useful behavioral context by noting that only tab metadata is returned and no cell data. However, it omits other behavioral traits such as pagination behavior or response format, leaving some gaps.

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

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

The description is two concise sentences, with the first sentence front-loading the core purpose and the second providing usage guidance. No unnecessary words or redundancy.

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

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

For a simple list tool with 5 optional parameters and no output schema, the description covers the essential aspects: scope, exclusions, and usage. The full parameter documentation exists in the schema, so the description is sufficiently complete, with only minor missing details like pagination defaults.

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

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

Schema description coverage is 100%, meaning all parameters are already well-documented in the schema. The description does not add extra parameter semantics beyond what the schema provides, so the baseline of 3 is appropriate.

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

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

The description uses a specific verb ('List') and resource ('spreadsheets') with added scope ('with their tab metadata (no cell data)'). It clearly distinguishes from sibling tools like list_documents and list_slides by naming the target resource type.

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 states when to use the tool: 'Use this when asked to list, find, or search spreadsheets, workbooks, tables, or tabular data.' This provides clear usage context, though it does not explicitly mention exclusions or 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?

With no annotations, the description carries the full burden of behavioral disclosure. It says 'List all' but the schema includes limit/offset, implying paginated results, so the phrase 'all' is misleading. It also fails to mention that results may be filtered by server_id or that pagination is needed to retrieve everything.

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

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

The description is two concise, front-loaded sentences. The first sentence states the core action and resource, and the second adds usage context. No wasted words or redundant information.

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

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

The description covers the tool's purpose and when to use it, which is adequate for a simple list operation. However, it lacks any mention of pagination behavior or return format, and the 'all' phrasing conflicts with the schema's limit/offset parameters, leaving some gaps in 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 coverage is 100%, so the schema already documents all five parameters with descriptions. The description adds no parameter-specific details, but the baseline of 3 applies since the schema is exhaustive.

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 ('List'), the resource ('slide presentations'), and includes helpful synonyms (slides, powerpoint, deck, keynote). It distinguishes this tool from siblings like list_documents or list_sheets by specifically targeting presentations/decks/slideshows.

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 says 'Use this when asked to list, find, or search presentations, decks, or slideshows,' providing clear when-to-use guidance. It does not explicitly mention alternatives (e.g., get_slide_presentation for a single item), but the context makes the intended usage 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 does state that content replaces the entire document body, but this is also already documented in the input schema's property description. The description does not mention permissions, reversibility, side effects, or what happens to other fields when only title or content is supplied. This is a significant gap 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 a single sentence of 17 words, immediately front-loading the verb and object. It includes the essential scope ('doc, word, note') and the key action ('replace the body') with no filler or redundant phrasing. Every part earns its place.

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

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

Given the tool's simplicity (3 parameters, no output schema) and the strong schema coverage, the description is largely sufficient. It covers the core update capability and the destructive nature of content replacement. It could mention that id is required and other fields are optional, but this is already clear from the schema. Overall, it is complete enough for an agent to use 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 coverage is 100%, so the baseline is 3. The description adds the 'and/or' qualifier, indicating that a call can include title, content, or both, which is a useful usage pattern not explicitly stated in the schema. However, the schema already provides clear descriptions for each parameter (e.g., 'New HTML content (replaces entire document body)'), so the description's additional value is marginal.

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

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

The description states the specific verb 'Update' and the resource 'existing document', further distinguishing it as handling doc, word, and note types. This clearly differentiates it from sibling tools like update_sheet or update_slide_presentation. The additional clause about supplying title and/or HTML content to replace the body further clarifies the tool's 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 implies usage by mentioning 'existing document', which signals this is for modifying already-created documents rather than creating new ones. However, it lacks explicit when-to-use or when-not-to-use guidance and does not name any alternative tools (e.g., create_document or delete_document). The context is clear but not fully explicit.

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

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

With no annotations, the description carries the burden. It adds the useful constraint 'currently only title' and implies it only updates that property. However, it does not disclose side effects, permissions, or reversibility, leaving some behavioral ambiguity for an update 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?

A single, well-structured sentence with no redundancy. It front-loads the action and resource, and the parenthetical limitation is concise and useful.

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 update tool with only two parameters and no output schema, the description is nearly sufficient. It states the scope and limitation, but the lack of any behavioral notes (e.g., whether the operation overwrites the existing title) is a minor gap given the absence of annotations.

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 covers 100% of the parameters with descriptions, so baseline is 3. The description adds meaning by clarifying that 'title' is the only supported workbook-level property and that the operation targets the workbook, which goes slightly beyond the schema's basic 'New title' and 'Sheet (workbook) ID'.

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 identifies the action ('Update'), the resource ('spreadsheet/sheet/workbook'), and the scope ('workbook-level properties'). It explicitly limits to 'currently only title', which distinguishes it from sibling tools like update_document and update_sheet_tab.

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 by specifying 'workbook-level properties', indicating this is for the workbook (not a tab or document). It does not explicitly name alternatives or exclusions, but the 'currently only title' limitation and the sibling names help the agent infer when to use this tool.

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

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

The description provides one behavioral hint: setting a cell value to null clears it. However, it lacks disclosure of side effects, partial update behavior, or what happens when resizing the grid, which is especially important given no annotations are present.

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

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

The two-sentence structure is efficient, but the first sentence is awkward with redundant parenthetical and the unverified 'merge cells' claim. It could be streamlined to focus on actual parameters.

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

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

For a tool with 7 parameters, nested objects, and no annotations or output schema, this description is incomplete. It doesn't cover error behavior, partial updates, or the full scope of formatting options, leaving the agent to rely solely on the schema.

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

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

Schema coverage is 100%, so baseline is 3, but the description adds nothing beyond the schema—it even mentions 'merge cells' which has no corresponding parameter. The null-clearing behavior is already documented in the schema's cells description.

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 updates a spreadsheet tab with actions like rename, change color, and resize. However, the mention of 'merge cells' is not reflected in the schema, creating ambiguity about the tool's actual capabilities.

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 instead of 'update_sheet' or other siblings. The description only states the general update purpose without defining exclusions or alternative 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?

There are no annotations, so the description must carry behavioral transparency. It states 'update' but does not disclose that the data parameter is a full replacement, what happens if fields are omitted, or whether changes are destructive. The schema mentions 'full replacement array' but the description itself lacks such context.

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

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

The description is a single, front-loaded sentence that clearly states the tool's purpose and main parameters. It is concise and contains no redundant information, though the parenthetical synonyms are slightly extra but still useful.

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?

This is a mutation tool with no annotations and no output schema, so the description should explain behavioral context and return values. It does neither. The schema covers parameters, but the description lacks important details like whether data replaces all slides and what the tool returns after the update.

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

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

Schema description coverage is 100%, so the baseline is 3. The description merely lists parameter names (title, slide data, theme, aspect ratio) without adding additional meaning or usage details beyond 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 clearly states the tool updates a slide presentation and lists the updatable aspects (title, slide data, theme, aspect ratio). It distinguishes itself from create/delete/get by using 'update' and from append_slides by implying full modification rather than appending. However, it does not explicitly name sibling 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 no guidance on when to use this tool versus alternatives. It does not mention append_slides for adding slides or create_slide_presentation for new presentations. Usage is only implied by the verb 'update'.

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