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

Annotations provide idempotentHint and destructiveHint. The description adds that the tool returns the updated task object, but does not specify behavior if the tag already exists. No contradiction with annotations.

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

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

The description is concise with a clear structure: brief summary, args list, returns, and examples. Every sentence serves a purpose.

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

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

Despite lacking an output schema, the description mentions the return value. Examples cover key use cases. For a simple modification tool, it is complete.

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

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

Schema coverage is 100%. The description adds value by explaining the priority between taskId and taskName and providing examples, which goes 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 'Add a tag to a task in OmniFocus', specifying the verb and resource. It distinguishes from sibling tools like omnifocus_remove_tag_from_task and omnifocus_batch_add_tag.

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 explains when to use taskId vs taskName and priority rules. However, it lacks explicit guidance on when not to use this tool (e.g., batch operations) 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?

Annotations confirm idempotent and non-desctructive behavior; the description elaborates by stating unchanged tasks and summarizing the return value (counts, updated tasks, failures). Adds value beyond annotations.

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

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

Well-structured with clear sections (Args, Returns, Examples) and a concise opening sentence. Slight redundancy with schema, but overall efficient.

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 batch tool with two parameters and annotations present, the description covers prerequisites, behavior, return value, and an example. No gaps.

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

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

Schema coverage is 100% with both parameters described in the schema. The description repeats this and adds an example, but does not significantly enhance understanding 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 it adds the same tag to multiple tasks in one operation, distinct from siblings like omnifocus_add_tag_to_task (single task) and omnifocus_batch_remove_tag (removes tags).

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?

Specifies that the tag must already exist and that tasks already having the tag are left unchanged, providing context for idempotent use. However, it does not explicitly mention when not to use or name alternative tools.

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

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

Annotations indicate non-readonly and non-destructive; description confirms it performs completes/drops. It adds batch size limits (1-100) and mentions per-task failures, which are useful behavioral details beyond annotations.

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

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

The description is concise with clear sections (Args, Returns, Examples). No fluff, every sentence is informative.

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 no output schema, the description explains return values (summary, updated tasks, failures) and constraints (batch size). It is sufficiently complete for a batched mutation tool.

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

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

Schema coverage is 100% so baseline is 3. Description provides examples and return info but adds little beyond schema for parameter meaning.

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 'Complete or drop multiple tasks in one operation.' This distinguishes it from single-task tools like omnifocus_complete_task and other batch 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 provides context for when to use this tool (batch operations) and includes examples. It does not explicitly exclude single-task scenarios, but the presence of a sibling tool for single completes implies differentiation.

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?

Describes the update effect on review status and includes return value (summary with count and errors). Annotations indicate mutation (readOnlyHint=false) but no destructive hint, which aligns.

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

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

Very concise with clear sections (Args, Returns, Examples). First sentence is direct. No redundant or unnecessary 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?

Completeness is high given no output schema: return value described, parameter constraints spelled out, examples provided, and no missing context for a batch review 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?

Schema coverage is 100%, and description adds value by restating constraints (1-100 projects, reviewIntervalDays optional range 1-3650) and providing examples. This clarifies usage beyond 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?

Description explicitly states 'Mark multiple projects as reviewed', which is a specific verb+resource. It clearly distinguishes from the sibling omnifocus_mark_project_reviewed by indicating batch operation.

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

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

While not explicitly stating when not to use vs single mark, the name and description imply it's for batch operations, and the sibling tool handles single projects. Could be improved with direct alternative mention.

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

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

Annotations indicate idempotency and non-destructiveness, and the description adds useful context: tasks without the tag are left unchanged, and a summary with counts and failures is returned.

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, well-structured with a clear purpose, behavior note, argument listing, return type, and example, all front-loaded for quick comprehension.

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 annotations, full schema, and no output schema, the description sufficiently covers behavior, inputs, output format, and provides an example, making it complete for a batch modification tool.

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

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

Schema coverage is 100%, and the description reiterates parameter details without adding new meaning 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 clearly states the tool removes the same tag from multiple tasks in one operation, distinguishing it from siblings like single-task removal or batch addition.

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 does not explicitly state when to use this tool versus alternatives, but the context from sibling names and the description's emphasis on batch operation imply its use case.

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

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

Adds critical behavior beyond annotations: detailed explanation of recurring task handling (complete advances, drop cancels series). No contradiction with annotations; idempotentHint true aligns with action semantics.

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

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

Well-structured with summary, args, note, returns, and examples. Every sentence is informative and non-redundant. No wasted words.

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

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

Covers purpose, all parameters with usage guidance, behavioral nuances, return value, and examples. No output schema but return description is sufficient. Fully equips agent to invoke correctly.

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

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

Schema coverage is 100%, but description adds value: explains priority rule, requirement of at least one, default for action, and provides clear examples that illustrate parameter 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?

Clearly states 'Mark a task as complete or dropped in OmniFocus' with specific verb and resource. Distinguishes from siblings like delete_task and batch_complete_task by focusing on single task completion/dropping.

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 recommends using taskId from list/search results or taskName for natural language. Provides priority rule when both provided and states required presence. Could improve by mentioning when to use batch alternatives, but context from sibling names helps.

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

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

Annotations indicate destructiveHint=false and readOnlyHint=false, consistent with creating a folder (a non-destructive mutation). The description details the behavior (top-level vs nested) and indicates a return value, adding transparency beyond annotations.

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

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

The description is concise and well-structured with a summary, parameter list, return value, and examples. Every sentence serves a purpose with no redundancy.

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

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

Given the simplicity of the tool (2 parameters, no output schema, basic annotations), the description fully covers the purpose, parameters, return value, and usage scenarios. No gaps remain.

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

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

Since schema coverage is 100%, the baseline is 3. The description adds value with examples showing how to use name and parentFolderName, clarifying their roles beyond schema descriptions.

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

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

The description clearly states the tool creates a folder in OmniFocus, distinguishing it from sibling tools like update_folder or delete_folder. It specifies top-level or nested creation, leaving no ambiguity.

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 (creating a new folder) and includes examples for top-level and nested usage. It doesn't explicitly state when not to use, but the purpose is self-evident 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?

Annotations indicate readOnlyHint=false and destructiveHint=false, which align with the creation behavior. The description adds value by explaining folder nesting and default status, though it doesn't detail side effects like overwriting or required permissions. No contradictions with annotations.

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

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

The description is well-structured with sections for Args, Returns, and Examples. Every sentence serves a purpose, with no redundancy or fluff. It is concise yet comprehensive.

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 8 parameters and no output schema, the description thoroughly explains each parameter and provides example usage. The return value is summarized, sufficient for a creation tool. The context (annotations, schema coverage) is fully leveraged.

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%, but the description adds meaningful context beyond the schema, such as mentioning ISO 8601 date formats, default values for flagged/sequential/status, and providing examples. This aids the agent in correctly formatting parameters.

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

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

The description explicitly states 'Create a new project in OmniFocus' and specifies top-level or folder placement, clearly distinguishing it from sibling tools like omnifocus_create_task, omnifocus_create_folder, and omnifocus_update_project.

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 clearly indicates when to use this tool (creating a project) and outlines optional properties. However, it lacks explicit guidance on when not to use it compared to alternatives like omnifocus_update_project, but the context of sibling names and the action verb provide adequate direction.

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

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

Annotations indicate a write operation (readOnlyHint=false) and not destructive. The description adds behavioral context: creation details, support for recurrence, return of task object, and no contradictions. It clarifies actions beyond annotations.

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

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

The description is well-structured with headings, bulleted parameters, and examples. It is somewhat lengthy but each part adds value. Could be slightly more concise, but organization compensates.

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 11 parameters, no output schema, the description covers all parameters comprehensively with examples. It explains the return value and common use cases. Missing only usage guidelines for more complete context.

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

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

Schema coverage is 100%, so baseline is 3. The description adds examples, clarifies relationships (e.g., parentTaskId overrides projectName), and explains recurrence object in detail. This significantly aids parameter 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 it creates a task in OmniFocus, specifying inbox or project, and lists numerous parameters. It distinguishes from siblings like update_task, delete_task, and batch 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 implies usage for creating tasks but does not explicitly state when to use or not use this tool versus alternatives like omnifocus_update_task or omnifocus_batch_complete_task. No exclusions are mentioned.

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?

Beyond the destructiveHint annotation, the description warns that deletion is permanent, includes cascading deletion of contents, and cannot be undone via MCP. This adds significant behavioral 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 compact, logically structured (overview, args, returns, examples), and front-loaded with the key action. No unnecessary words.

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

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

Given full schema coverage and annotations, the description provides examples, parameter interaction rules, and return type. For a destructive delete operation, it covers all necessary context.

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

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

Schema coverage is 100%, so baseline is 3. The description adds priority rules (folderId takes precedence), explains the mutual requirement, and provides concrete examples, enhancing the schema descriptions.

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

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

The description uses a specific verb ('Permanently delete') and resource ('folder from OmniFocus'), and clearly states the scope ('including any projects and folders it contains'). This distinguishes it from sibling tools like omnifocus_create_folder and omnifocus_update_folder.

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 explains how to provide the folder identifier (ID or name), that at least one is required, and that ID takes priority. It also notes permanence and irreversibility. While it doesn't explicitly contrast with omnifocus_delete_project or omnifocus_delete_task, the context is clear.

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

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

Annotations indicate destructiveHint=true, but the description adds valuable context: the action is permanent and includes the project’s tasks. This goes beyond the annotation, though it could mention irreversible consequences for linked data.

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, front-loaded with the core action, and includes structured Args, Returns, and Examples sections. No unnecessary words.

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

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

Given the simplicity of the tool and no output schema, the description fully covers what the tool does, how to use it, and what to expect as a return. Examples further clarify 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?

The input schema already covers both parameters with descriptions (100% coverage). The description adds priority logic (projectId takes priority) and the at-least-one requirement, which is not in the schema.

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

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

The description clearly states the tool permanently deletes a project and its tasks, distinguishing it from sibling tools like omnifocus_delete_folder or omnifocus_delete_task. The verb 'delete' matches the title, and the scope is well-defined.

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 guidance on how to specify the target (by ID or name) and that at least one parameter is required. It does not explicitly mention when to use versus alternatives, but for a delete operation this is sufficient.

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 adds significant context beyond the destructiveHint annotation by stating it's permanent and cannot be undone via MCP. It also explains parameter priority, aligning with and enhancing annotation info.

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

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

The description is front-loaded with the core action and permanence, followed by structured parameter details, return info, and examples. Every sentence adds value without redundancy.

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

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

For a delete tool with two parameters and no output schema, the description fully explains usage, parameter selection, and return value. No critical information is missing given the tool's simplicity.

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

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

The input schema already covers both parameters with descriptions (100% coverage). The description adds value by specifying priority and providing examples, making it clearer than 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 it permanently deletes a task from OmniFocus and that it cannot be undone via MCP. This distinguishes it from sibling tools like complete_task or update_task, which are non-destructive.

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

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

Provides clear guidance on using taskId or taskName, with priority for taskId. However, it does not explicitly state when not to use it, such as when only completion is needed, though sibling tools imply alternatives.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds return format ('Array of due tasks sorted by due date'), which is useful but not significantly beyond annotations.

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

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

Well-structured with clear Args, Returns, and Examples sections. Every sentence adds value; no redundancy. Concise but informative.

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

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

Covers input semantics well and mentions return format. However, without output schema, description of returned task structure is minimal; more detail on fields would improve 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%, but description adds value with defaults, constraints (0-365 days, 1-500 tasks), and detailed tagMatchMode explanation. Examples further clarify parameter 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?

Description clearly states 'Get tasks that are due within a specified timeframe' with specific verb and resource. Distinguishes from sibling get-tools (e.g., get_flagged_tasks) by focusing on due dates.

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?

Includes examples for common scenarios (due this week, today, 30 days) which imply usage contexts. However, no explicit guidance on when to use this tool versus alternatives like omnifocus_search or omnifocus_get_planned_tasks.

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 thoroughly explains behavior beyond annotations: default values, constraints (limit 1-500, tags max 20), conditional logic (tagMatchMode only applied when tags provided), and examples. Annotations confirm read-only, idempotent, non-destructive, so no contradictions.

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

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

The description is very concise and well-structured: clear purpose, then Args, Returns, Examples. No fluff, every sentence adds value. Front-loaded with the main goal.

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 low complexity, full parameter documentation, and no output schema, the description is complete. It covers what the tool returns, all parameters with defaults, and example invocations. No missing information for an agent to use it correctly.

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

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

Schema coverage is 100% with descriptions, but the tool description adds value by organizing parameters in a clear list and providing examples that show typical usage patterns (e.g., empty object for active tasks, includeCompleted: true). This enhances understanding beyond 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 'Get all flagged tasks in OmniFocus' with a specific verb and resource. It distinguishes itself from sibling tools like omnifocus_get_due_tasks by focusing solely on flagged tasks.

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

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

The description implies usage when flagged tasks are needed but does not provide explicit guidance on when to use this tool over alternatives. No when-not-to-use or comparison with sibling tools.

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

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

Annotations (readOnlyHint, destructiveHint) already indicate safety. Description adds valuable behavioral context: switching the front window and restoring the original perspective, which is not captured by annotations.

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

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

Description is front-loaded with purpose, followed by behavioral note, then clearly structured Args, Returns, and Examples. Every sentence earns its place 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?

Despite no output schema, description lists all return fields. It explains the window-switching side effect and restoration. Tool is simple but all necessary info is provided.

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

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

Schema coverage is 100%, but description adds value by suggesting how to find perspective names and providing examples with default limit, going beyond schema definitions.

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

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

Description clearly states 'Get tasks shown in a specific OmniFocus perspective' and explains the switching/restoring behavior, distinguishing it from sibling tools like get_project_tasks or list_inbox.

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

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

Provides guidance to use omnifocus_list_perspectives for finding perspective names and includes examples. While it doesn't explicitly exclude alternatives, the context makes it clear 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?

Annotations indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, which are consistent. The description adds important behavior: returns array sorted by planned date, default parameter values, and tag matching logic. No contradictions.

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

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

The description is well-structured: purpose paragraph, parameter list, return type, and examples. Every sentence is informative and front-loaded with the core purpose. No unnecessary words.

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

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

Given no output schema, the description covers the tool's purpose, parameters, and return type adequately. It could specify the structure of returned task objects, but the examples and sort order are sufficient 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% with parameter descriptions. The description adds meaning beyond schema by explaining the concept of planned dates and providing examples. It does not repeat schema details but enriches 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 clearly states 'Get tasks that are planned within a specified timeframe' with a specific verb and resource, and distinguishes from sibling tools like omnifocus_get_due_tasks by emphasizing the 'planned dates' concept separate from due dates.

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 explains when to use this tool (for planned tasks) but does not explicitly state when not to use it or name alternatives. However, the parameter descriptions and examples provide clear context for usage.

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

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

Annotations already indicate read-only, idempotent, non-destructive. The description adds sorting by next review date and filtering details, but does not disclose return format or pagination. No contradictions with annotations.

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

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

The description is efficiently structured: purpose sentence, then a bullet-like listing of args with defaults and constraints, examples, and return type. No wasted words, well-organized.

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?

No output schema exists, so description should explain return structure. It only mentions 'Array of projects needing review sorted by next review date' without field details. Contextually adequate for a simple filtered list but could specify project fields.

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% (all parameters described). The description repeats schema info and adds examples, clarifying 'daysAhead' as overdue vs. due. However, it provides minimal extra meaning beyond the existing schema descriptions.

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

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

The description clearly states it gets projects needing review based on next review date, with specific criteria (overdue or within days ahead). It distinguishes from siblings like omnifocus_list_projects by focusing on review status.

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 implicitly suggests use for review filtering, with examples showing different scenarios. However, it does not explicitly state when alternatives like omnifocus_list_projects or omnifocus_get_project_tasks are better, missing explicit exclusions.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the safety profile is clear. The description adds that it returns tasks including subtasks and specifies the return format, providing behavior beyond annotations.

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

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

The description is well-structured with a purpose sentence, return description, usage prerequisite, args and returns in a clean list, and examples. Every sentence adds value and it's 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?

Despite no output schema, the description fully details the return format (fields) and provides examples. It covers all necessary context for using the tool correctly.

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

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

Schema coverage is 100% with all parameters described. The description reiterates the parameters and adds example usage, but doesn't add significant new meaning beyond the schema. Baseline 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 'Get all tasks belonging to a specific project in OmniFocus' with a specific verb and resource. It distinguishes from sibling tools like omnifocus_list_projects by mentioning that tool for finding project IDs first.

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 guides to use omnifocus_list_projects first to get project IDs. Though it doesn't list when not to use or alternatives, the context is clear given sibling tools have distinct 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?

Annotations already declare readOnlyHint true and destructiveHint false. The description adds value by detailing return fields (id, name, status, projectCount, folderCount, parentName) and examples, beyond what annotations provide.

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

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

The description is concise with three short paragraphs (overview, args, returns) plus examples. Every sentence is informative and well-structured, front-loading the core purpose.

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

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

Despite lacking an output schema, the description fully explains the return array structure with field names. It covers all necessary information for a list tool: purpose, arguments with defaults, and return format.

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

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

Input schema has 100% coverage with descriptions for both parameters. The description repeats this info and adds examples, but does not significantly extend meaning beyond the schema. Baseline 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 'List folders in OmniFocus' and explains that folders organize projects hierarchically. It distinguishes itself from sibling list tools (e.g., omnifocus_list_projects) by focusing specifically on folders.

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 examples and defaults but does not explicitly state when to use this tool versus alternatives like omnifocus_list_projects or omnifocus_search. Usage context is implied but lacks explicit when-not-to-use guidance.

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

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

Annotations already indicate readOnlyHint and idempotentHint. The description adds behavioral context (returns unassigned tasks) and explains tagMatchMode mechanics, which goes beyond what annotations provide.

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

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

The description is well-structured with clear sections for purpose, arguments, returns, and examples. Every sentence adds value 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?

Despite no output schema, the description lists return fields and provides relevant examples. It fully covers what the tool does, its parameters, and usage context.

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

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

Schema coverage is 100%, so a baseline of 3 applies. The description adds value through examples and clarifications (e.g., tagMatchMode behavior), raising the score to 4.

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 tasks in the OmniFocus inbox' and explains these are tasks not assigned to a project, distinguishing it from other task-listing tools like omnifocus_get_project_tasks.

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

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

The description implies usage for viewing newly captured items awaiting processing. While it does not explicitly exclude scenarios, the context is clear enough to differentiate from project-specific lists.

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

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

Annotations already provide readOnlyHint, destructiveHint, idempotentHint. Description adds return format (array of perspective objects with id, name) but no additional behavioral traits like pagination or performance. 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?

Well-structured with Args and Returns sections, concise with no extraneous text. Slightly verbose in the opening line but overall efficient.

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 low complexity (one optional parameter, no output schema, rich annotations), description is sufficiently complete. Explains what perspectives are and return shape. No major gaps.

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

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

Schema coverage is 100% with detailed description of limit parameter. Description restates schema info but does not add new meaning beyond formatting or examples. Baseline 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?

Clearly states the verb 'list' and resource 'perspectives', and distinguishes from sibling tools like omnifocus_list_folders and omnifocus_list_projects by specifying 'perspectives' as saved views/filters.

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 explicit guidance on when to use this tool versus alternatives (e.g., omnifocus_get_perspective_tasks). Only minimal examples of usage but no context on selection criteria or exclusions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral details beyond annotations, such as default status='active', limit default, folderName partial match, and return fields. No contradictions.

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

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

The description is well-structured with separate sections for purpose, arguments, returns, and examples. It is concise yet comprehensive, with no wasted words.

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

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

Despite lacking an output schema, the description explicitly lists return fields and provides examples covering typical use cases. It fully equips an agent to understand the tool's 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 coverage is 100%, but the description adds meaningful context: explains status enum values, folderName as partial match, and limit range. Examples further clarify usage. This adds value 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 'List projects in OmniFocus' and specifies the returned fields (status, dates, folder info). It distinguishes itself from sibling tools like omnifocus_list_folders or omnifocus_list_inbox by focusing on projects.

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 explains the tool's purpose and provides examples, but does not explicitly state when not to use it or compare it to alternatives like omnifocus_get_project_tasks. However, the context is clear enough for an agent to decide based on the need for listing projects.

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

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

Annotations declare readOnlyHint and idempotentHint, which the description reinforces by describing a non-destructive list operation. The description adds the return format (fields like id, name, status, etc.) and example invocations, providing behavioral context beyond the annotations.

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

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

Description is very concise with clear sections (Args, Returns, Examples). No extraneous text. Every sentence adds value. Well-structured and front-loaded.

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

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

For a simple read-only list tool with two parameters and no output schema, the description is complete. It specifies input parameters with defaults and return fields. It could mention ordering or pagination, but not essential given tool simplicity.

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

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

Schema description coverage is 100%, so baseline is 3. The description repeats parameter details (status enum values, limit range) and provides default values, but adds minimal extra meaning beyond the schema. Examples illustrate usage but do not significantly deepen 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?

Description clearly states 'List tags in OmniFocus' with explanation that tags are used to categorize tasks. This is a specific verb+resource combination that distinguishes from sibling tools like omnifocus_add_tag_to_task or omnifocus_create_task.

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 explicit guidance on when to use this tool versus alternatives. The purpose is obvious for a list operation, but the description lacks comparison to other tag-related tools or conditions for selecting 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?

Annotations indicate mutability (readOnlyHint: false). The description adds that the next review date is set based on the project's review interval or a custom interval. No contradictions found.

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

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

The description is concise, well-structured with Args and Examples sections. Every sentence adds value without redundancy.

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

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

Despite no output schema, the description mentions the return value (updated project object). All parameters are well-documented, and examples cover common use cases. Sufficient 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?

With 100% schema coverage, the baseline is 3. The description adds value by clarifying the priority of projectId over projectName and explaining reviewIntervalDays defaults. Examples further illustrate usage.

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

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

The description clearly states 'Mark a project as reviewed and update its next review date', with a specific verb and resource. It distinguishes from sibling tools like omnifocus_batch_mark_reviewed by being single-project.

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 explains when to use projectId vs projectName and provides examples. It implicitly says to use this for single projects vs batch. However, it doesn't explicitly mention when not to use or list alternatives.

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

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

Annotations indicate idempotentHint=true, destructiveHint=false. Description confirms removal and returns updated object, adding context about priority of identifiers. No contradiction.

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

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

Concise description with structured sections (Args, Returns, Examples). No wasted words. Front-loaded with purpose.

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

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

No output schema, but description specifies return type ('updated task object'). For a simple mutation with 3 params, this covers essential context. Lacks error handling details.

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 100%, but description adds meaning: priority rule (taskId over taskName), optionality, and example usages. This exceeds the schema's descriptions.

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

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

Clearly states 'Remove a tag from a task in OmniFocus.' Distinguishes from siblings like omnifocus_add_tag_to_task and omnifocus_batch_remove_tag by focusing on a single task.

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

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

Provides clear guidance on using taskId vs taskName with priority rules and at-least-one requirement. Gives examples. Could explicitly note that batch removal is done via a sibling 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?

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, which the description does not contradict. It adds that the tool uses 'smart matching,' providing extra behavioral 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?

Well-structured with an intro, Args section, Returns, and Examples. Concise and to the point without 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?

The description covers key aspects: what it searches, parameters, return format. With no output schema, the description compensates adequately. Could explicitly state read-only nature, but annotations cover that.

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 description adds value by providing defaults, examples, and explaining return format. This goes beyond what the schema alone provides.

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

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

Clearly states the action (search) and the resources (tasks, projects, folders, tags). Distinguishes from sibling tools that perform other operations like add, delete, list, etc.

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

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

Includes examples and parameter descriptions that clarify usage. While it doesn't explicitly state when not to use, the purpose is clear and the siblings are distinct operations.

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

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

Annotations indicate a mutation tool (readOnlyHint=false). The description confirms the rename behavior and adds transparency about the unsupported move operation. No contradiction with annotations.

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

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

The description is well-structured with labeled sections (Args, Note, Returns, Examples), concise sentences, and no redundant information. Every sentence adds value.

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

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

For a simple rename tool, the description fully covers the action, parameter usage, unsupported operations, return value, and examples. No missing context given the lack of output 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%, but the description enhances understanding by clarifying parameter priority (folderId > folderName) and providing examples that demonstrate usage patterns.

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 'Rename an existing folder in OmniFocus,' specifying the verb 'rename' and the resource 'folder.' It effectively differentiates from sibling tools like 'create_folder' and 'delete_folder.'

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 explains the order of priority between 'folderId' and 'folderName,' and notes the unsupported move operation with a suggested workaround. It lacks explicit when-not-to-use guidance, but the context is clear.

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

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

The description discloses important behaviors: only provided fields are changed, null clears fields, status transitions (completing with 'done' vs 'dropped', reactivation). It also transparently notes the unsupported move operation with an explanation. This goes beyond the basic annotations (which only indicate non-readOnly).

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 somewhat lengthy but well-structured: purpose first, then parameter details, then a note on limitation, then returns, then examples. Every sentence adds value. A minor deduction for verbosity; could be more terse for agent consumption, but still effective.

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

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

Given 10 parameters, no output schema, and no nested objects, the description covers all parameters with examples and notes limitations. It mentions return value ('The updated project object') but doesn't detail its structure. However, without an output schema, this is adequate. The description 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 baseline is 3. The description adds value by explaining usage semantics: null clears fields, status effects (e.g., setting 'done' completes), and the priority between projectId/projectName. Examples further clarify parameter usage. This raises the score above baseline.

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 'Update properties of an existing project in OmniFocus,' specifies the specific fields that can be updated, and distinguishes itself from siblings like omnifocus_update_project_note and omnifocus_create_project. It also notes a limitation (moving folders not supported) which clarifies 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 explains when to use this tool: for updating any project property. It provides constraints like the priority of projectId over projectName and the requirement of at least one identifier. It also warns about the unsupported move operation. However, it does not explicitly guide the agent on when to choose this over other update tools like omnifocus_update_project_note, though the sibling names imply the distinction.

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

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

Annotations indicate idempotent, non-destructive write; the description adds behavioral details: empty string clears the note, append flag behavior, and priority of projectId over projectName. No contradiction with annotations, and it goes beyond structured fields to provide useful nuance.

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

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

The description is well-structured with a clear header, args list, returns note, and examples. It is concise yet complete, front-loading the main purpose and providing necessary details without excess verbiage.

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 (1 required) and no output schema, the description covers all input parameters with examples, explains the return type (updated project object), and handles edge cases like clearing and appending. No gaps observed.

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% with descriptions for all 4 parameters. The description adds value by explaining priority logic (projectId takes precedence), requiredness (at least one of projectId/projectName), and the effect of empty string on note. This goes beyond the schema's basic descriptions.

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

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

The description clearly states 'Update the note/description on an existing project in OmniFocus.' The verb 'update' and resource 'project note' are specific and unambiguous, distinguishing it from sibling tools like omnifocus_update_project (which updates other fields) and omnifocus_update_task_note (for task notes).

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 scenarios for use (set by ID, by name, clear, append) through examples and parameter explanations. It does not explicitly state when not to use it or compare to alternatives, but the context is sufficient for typical use cases.

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

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

The description adds context beyond annotations by detailing partial update behavior, null clearing, taskId/taskName priority, and return value. Annotations are consistent (write operation, not destructive, not idempotent).

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

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

The description is long but well-structured with Args, Returns, and Examples sections. It is front-loaded with purpose. Minor redundancy (e.g., clearRecurrence explanation could be shorter) but overall efficient.

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 13 parameters and no output schema, the description covers all parameters, return value, special behaviors (null clearing, priority), and multiple examples. It is complete for a complex update tool.

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

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

Schema coverage is 100%, and the description adds significant meaning: structured breakdown of all 13 parameters, type info, null handling, and examples. It references 'same shape as create_task' for recurrence, adding 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 'Update properties of an existing task in OmniFocus' with a specific verb and resource. It distinguishes from siblings like create_task, complete_task, and delete_task by focusing on updating existing tasks.

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

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

The description explains partial updates ('Only the fields you provide are changed'), how to clear fields with null, and priority between taskId and taskName. It provides examples but does not explicitly contrast with alternative tools like omnifocus_update_task_note or batch 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?

Beyond annotations (idempotentHint=true, destructiveHint=false), description clarifies the append behavior, clearing note with empty string, and return value. No contradictions.

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

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

Description is concise with clear sections (Args, Returns, Examples). Every sentence adds value; no fluff.

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

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

Despite no output schema, description specifies the return value. Covers all parameters, edge cases (clear, append), and examples. Highly complete for a simple tool.

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

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

Schema coverage is 100%. The description adds meaning: priority between taskId/taskName, examples for each usage, and append semantics. Exceeds baseline.

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 'update' and resource 'note/description' on a task, and is distinct from sibling tools like omnifocus_update_task (which updates other fields) and omnifocus_update_project_note.

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 explains when to use taskId vs taskName with priority rules, and shows examples. It doesn't explicitly exclude alternatives but the purpose is clear for note updates.

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