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 clearly states the tool appends a timestamped note without erasing existing content, which is helpful. However, it does not disclose other behavioral traits such as whether the note is appended as plain text or markdown, character limits, or what happens if the task already has a note. The description is adequate but not comprehensive.

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-loading the key action and benefit. Every sentence adds value: the first explains core behavior (append without erasing), and the second clarifies when to use it. No redundant or vague wording.

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 3 required parameters, no output schema, and no annotations, the description provides essential context but is incomplete. It does not explain what the tool returns (e.g., success status, updated task object), nor does it mention error conditions (e.g., invalid list_id). For a tool in this context, more detail on output and error handling 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 description coverage is 0%, meaning the input schema provides no meaningful descriptions for the three required parameters. The description adds context for the 'note' parameter by explaining it will be timestamped and appended. However, it does not clarify the format or constraints for 'list_id' and 'task_id' (e.g., whether they are GUIDs or names). The lack of parameter-level descriptions is a gap, but the high-level semantics are partially addressed.

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 ('Append') and a clear resource ('Microsoft To Do task's notes/body'), and explicitly distinguishes this tool from tools that might overwrite content by stating 'WITHOUT erasing existing content'. It also contrasts with other sibling tools like todo_create_task or todo_update_task by focusing on adding notes rather than creating or updating entire 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 says to use the tool 'to record explanations, decisions, or what was done on a task', which implies use cases. However, it does not explicitly state when not to use it or mention alternative tools for different scenarios (e.g., using todo_update_task to overwrite notes). It lacks guidance on prerequisites like needing a list_id and task_id from other 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 carries the full burden. It discloses the three mutation operations (add, check, uncheck), but it does not describe error behavior, side effects, or permissions required. The behavioral disclosure is minimal but not misleading.

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 efficiently communicates the actions and a key constraint. No redundant information, and it front-loads the core verb and resource.

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 5 parameters, no output schema, and no annotations, the description is sparse. It does not explain the purpose of list_id or task_id, nor does it discuss return values or error cases. While the tool is simple, additional context would be beneficial for correct usage.

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

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

Schema description coverage is 60%. The description restates the operations (add, check, uncheck) already documented in the schema, and adds the constraint that at least one must be provided. However, the required parameters list_id and task_id are not explained in either the schema or the description, leaving a gap.

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

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

The description clearly states the specific actions (add, check, uncheck) and the resource (checklist subtasks on a Microsoft To Do task). It distinguishes from sibling tools like todo_complete_tasks and todo_update_task, which handle different aspects of tasks.

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

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

The description provides one usage constraint ('Provide at least one of add / check / uncheck'), but it lacks explicit guidance on when to use this tool vs. alternatives, and it does not mention when not to use it or 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?

No annotations are provided, so the description must cover behavioral traits. It states it is 'batch-friendly' and marks tasks as completed (mutative behavior). However, it does not disclose whether this is reversible, what happens if some tasks fail (partial success), or auth/permission requirements, 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 three concise sentences with no wasted words. It front-loads the core purpose and then provides usage hints. It earns its place, but could be slightly more structured (e.g., separating purpose and usage context).

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

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

Given the tool's simplicity (2 params, no nested objects, no output schema), the description is mostly complete. It tells the agent how to get input and how to batch. It would benefit from mentioning the success/error response shape or whether tasks are permanently deleted or just marked done, but overall sufficient for a straightforward mutation.

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

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

Schema description coverage is 0%, so the description must compensate. It explains that 'list_id' comes from todo_get_tasks and 'task_ids' are 'task ids' from the same source, adding meaning beyond the bare schema types. It also clarifies the batch nature by saying 'pass every finished task id at once'. This is helpful but could be more precise about formats 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 clearly states the verb 'Mark' and the resource 'Microsoft To Do tasks as completed', and distinguishes itself from siblings like todo_get_tasks by mentioning input from that tool. It explicitly says 'batch-friendly', which differentiates it from single-task operations like todo_update_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?

The description advises to 'pass every finished task id at once' and to use the ids returned by todo_get_tasks, giving clear when-to-use context. However, it does not explicitly state when not to use this tool (e.g., if tasks need partial updates, use todo_update_task instead), so it misses some comparative 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?

No annotations are present, so the description must fully disclose behavior. It states creation with optional fields but omits authentication requirements, error handling (e.g., invalid list), rate limits, or whether the created task is returned. For a mutation tool, this is insufficient.

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 18-word sentence that front-loads the main verb and resource, followed by a clear enumeration of optional features. No redundant words. Efficiently conveys the core functionality.

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 7 parameters, no annotations, and no output schema, the description should cover prerequisites, how to specify the list, and what happens on success or error. It only describes the action and optional fields, leaving many operational gaps. Incomplete for an agent to use reliably.

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 only 43% (3 of 7 params described). The description merely lists the optional fields (notes, due date, importance, checklist), which minimally adds to the schema but does not clarify the 'group' parameter, how 'list' is identified (ID vs name), or 'title' constraints. It does not compensate for the low coverage.

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

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

The description uses a specific verb ('Create a new task'), identifies the resource ('Microsoft To Do list'), and lists optional fields (notes, due date, importance, checklist subtasks). This clearly distinguishes it from siblings like 'todo_update_task' or 'todo_add_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?

No guidance is provided on when to use this tool versus alternatives (e.g., 'todo_update_task' for modifying, 'todo_complete_tasks' for completion). No prerequisites like requiring prior login or valid list IDs 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?

No annotations are provided, so the description carries the full burden. It mentions side effects: 'refreshes the group mapping and reports any renamed or deleted lists.' This adds useful behavioral context. However, it does not disclose whether the tool is read-only, requires authentication, or has rate limits. The description adds value but is not fully comprehensive.

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 short sentences, each adding value. The first sentence states the core purpose, the second gives usage guidance, and the third explains additional behavior. No unnecessary words, and it is front-loaded with the most important 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 tool has no parameters, no output schema, and no annotations, so the description is the sole source of context. It covers purpose, usage, and side effects, but does not describe the output format (e.g., list names, IDs, group structure). For a listing tool, omitting return structure leaves a gap for the agent to understand what data to expect.

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

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

There are no parameters, and schema coverage is 100%. The baseline for 0 parameters is 4. The description does not need to add parameter semantics, and it correctly avoids extraneous information.

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 it lists all Microsoft To Do lists organized by group/folder. The verb 'list' and resource 'To Do lists' are specific, and the title reinforces the purpose. It clearly distinguishes from sibling tools like todo_get_tasks by focusing on lists.

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 directly tells when to use: 'Use when the user asks what lists they have, or to disambiguate a list name.' This provides clear context. It does not explicitly mention when not to use or alternative tools, but the guidance is sufficient for most 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?

With no annotations, the description carries the full burden. It clearly states the tool is a read operation (fetch), specifies the return fields (titles, status, due dates, notes, checklist subtasks), and reveals the default behavior (open tasks only). This goes beyond the schema, which only describes parameters. However, it does not mention authentication requirements, rate limits, or error conditions, which would push it to 5.

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

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

The description is concise with three short sentences that are front-loaded with the core action. Each sentence adds value: the first states the primary action and scoping, the second enumerates return fields, the third explains defaults. No extraneous words or repetition.

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 (4 parameters, no output schema, no annotations), the description is largely complete. It explains what the tool does, what it returns, and the default state. It could be more complete by mentioning pagination limits, ordering, or prerequisites (e.g., needing list names from todo_get_lists), but overall it provides sufficient context 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 description coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining the overall purpose ('by name, optionally scoped to a group/folder') and the default behavior ('Defaults to open not completed tasks only'). It also clarifies what the include_details parameter affects (returns notes and checklist items). This additional context elevates the score.

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

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

The description uses a specific verb ('Fetch') and resource ('tasks from a Microsoft To Do list'), and distinguishes from sibling tools like todo_get_lists (which retrieves lists, not tasks) and todo_create_task (which creates tasks). The optional scoping to a group/folder further clarifies the tool's unique capability.

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 context (fetching tasks from a named list, optionally scoped to a group), but does not explicitly state when to use this tool versus alternatives (e.g., when to use todo_get_lists, todo_create_task, or todo_complete_tasks). No when-not or alternative guidance is provided, so usage is only implied.

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 bears full burden. It clearly states the tool uses device-code flow, returns a URL and code without blocking, and can report current status. This fully describes behavioral traits like non-blocking nature and output format, exceeding typical minimal disclosures.

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?

Two sentences clearly front-load the core purpose and usage trigger, with second sentence specifying non-blocking behavior. Every sentence earns its place; no filler or redundancy.

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

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

Given zero parameters, no output schema, and no annotations, the description fully covers what the agent needs: purpose, trigger condition, device-code flow, non-blocking nature, and what to return to user. No gaps remain for this 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?

The tool has zero parameters and schema coverage is 100%, so description need not add param info. The description briefly mentions the return values (sign-in URL and code), which adds some utility beyond an empty schema. A score of 4 is appropriate as it compensates with behavioral context.

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 ('Sign in') and a clear resource ('Microsoft To Do account'), explicitly mentioning the device-code flow and dual functionality (sign-in vs. status check). It distinguishes from siblings, which are all task/list management tools that require a signed-in state.

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 when-to-use guidance: 'Call this whenever another To Do tool returns error 'not_signed_in'.' It also clarifies that this does not block waiting, implying the agent should relay the URL and code to the user. No alternatives are needed given the tool's unique role.

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 carry the full behavioral burden. It reveals that the tool modifies group assignments and can clear them (set to null), implying mutable behavior. However, it does not mention side effects, required permissions, or whether the operation is idempotent. The description adds value beyond the schema but has 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 concise at two sentences, front-loading the main purpose. The first sentence covers the primary use, and the second sentence adds minor details about sub-uses and parameter types. Every sentence adds value, though it could be slightly more compact without losing clarity.

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 there are no annotations, no output schema, and only one parameter with nested objects, the description covers the tool's core behavior but lacks information on return values or what happens on failure. The context is adequate for a simple assignment tool, but a bit more could help the agent understand the response or error cases.

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

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

Schema description coverage is 0%, so the description must compensate. It explains that 'list' can be a name or listId, and 'group' can be a group name or null to clear, adding meaning beyond the schema's types. This clarifies the parameter semantics effectively.

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 'Assign' and the resource 'Microsoft To Do lists to named groups/folders', and distinguishes this tool from siblings like todo_get_lists by explaining the purpose is to organize lists into groups for later retrieval. It also mentions sub-uses like moving or clearing assignments.

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

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

The description gives explicit use cases (assign lists to groups, move a list to a different group, clear a group) but does not specify when not to use this tool versus alternatives such as creating a list or login. No sibling is directly excluded, but the use cases are 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 must fully disclose behavior. It hints at mutation (update) but does not state whether updates are partial (PATCH-like) or full replacement, whether it returns the updated object, or any side effects (e.g., notifications). The basics of setting status to 'notStarted' are covered, but deeper behavioral expectations are 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 two concise sentences with upfront purpose and two specific tips. It is well-structured and easy to parse, though the tips could be bulleted for even faster scanning.

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

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

Given the tool has 6 parameters (2 required), no output schema, and no annotations, the description should provide more context on return values, error conditions (e.g., invalid list_id), and behavior of partial updates. The current description leaves significant gaps for an agent to use the tool reliably.

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 only 17% (only due_date has a description). The description adds value by explaining how to use 'status' for reopening (notStarted) and 'due_date' for clearing (null), but does not clarify the semantics of 'importance' or whether 'title' replaces or appends. With 6 parameters, more parameter guidance is needed.

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 Microsoft To Do task and lists the editable fields (title, due date, importance, status). It is specific and distinct from siblings like todo_create_task or todo_complete_tasks, though it could better differentiate from todo_checklist or todo_add_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 provides specific usage tips for reopening tasks and clearing due dates, which is helpful. However, it does not mention when to use this tool versus alternatives like todo_complete_tasks, todo_checklist, or todo_add_note, nor does it state prerequisites (e.g., list must exist).

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