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

Annotations already indicate a write operation (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds the permission requirement but lacks details about side effects like notifications or task updates.

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 extremely concise with two sentences, front-loading the action and adding a necessary permission note. No unnecessary content.

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?

While the description covers the basic purpose, it does not explain return values, error conditions, or the relationship between cardId and taskNumber. Given the tool's simplicity, this is adequate but not complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add additional context beyond what the schema provides for each parameter.

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

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

The description clearly states the verb 'Adds' and the resource 'a comment to a task', which distinguishes it from siblings like update_comment and delete_comment.

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., add_task_subscriber) or when not to use it. Only a permission requirement is 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?

The description adds behavioral detail beyond annotations: it explains the bidirectional update (child's parentTask set, parent's subtaskRefs appended) and that tasks can be on different cards. Annotations only indicate non-read-only and non-destructive nature.

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, both front-loaded with core purpose. Every sentence adds essential context 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?

The description covers the core operation, board constraint, and both sides of the relationship. It doesn't describe return value or error cases, but no output schema exists, so this is acceptable. Could briefly mention success confirmation.

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

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

Schema coverage is 100%, so the schema documents each parameter. The description adds value by explaining the relationship between parameters (parent and child pair) and the board containment requirement, which aids correct invocation.

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

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

The description clearly states the tool links two tasks in a parent-child relationship, specifying the bidirectional update (child's parentTask set, parent's subtaskRefs array gains child). It effectively distinguishes from siblings like remove_subtask and list_subtasks.

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 when to use the tool (to create a subtask relationship) without explicit when-not-to-use guidance. However, given the sibling tools, the usage context is clear enough.

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

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

Annotations indicate write but non-destructive. The description confirms 'attach' but does not disclose additional behaviors like overwrite behavior, permission requirements, or error handling. It adds minimal value 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?

Single sentence, no wasted words. Front-loaded with verb and resource. Highly concise.

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

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

For a simple mutation tool with no output schema, the description conveys the essential action. It lacks mention of the result or side effects (e.g., attachment confirmation), but this is common for such tools. Overall, adequate but not fully comprehensive.

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

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

Schema descriptions cover all 5 parameters, each with a brief description. The tool description redundantly states that fileId must come from list_files, which is already in the schema. No additional parameter details are provided beyond schema, so baseline score of 3 is appropriate.

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

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

Description clearly states the action (attach) and resources (existing workspace file to a task). It distinguishes from siblings like add_comment or add_subtask by specifying attachment of a file. The mention that the file ID must come from list_files adds precision.

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 a key usage guideline: the file ID must come from list_files. It does not explicitly contrast with removing or listing attachments, but for the intended use it is sufficient. Could be improved by noting when to use sibling tools like remove_task_attachment.

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 (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds that the subscriber receives notifications, which is useful. However, it does not disclose other behavioral traits such as idempotency, permission requirements, or behavior if the member is already subscribed.

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 conveys the purpose and effect efficiently. It is front-loaded with the action and resource, with no wasted words.

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

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

Given the tool's low complexity (5 parameters, no output schema), the description adequately explains the core functionality and outcome. It does not need to explain return values. The context is complete for an 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% with descriptions for all parameters. The description does not add meaning beyond the schema, e.g., it mentions 'workspace member' which maps to 'uid', but no additional semantics. 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 specifies the action ('Add a workspace member as a subscriber on a task') and the resulting effect ('they'll receive notifications when the task is updated, commented on, etc.'). It distinguishes from siblings like 'remove_task_subscriber' by focusing on addition, and 'subscribe_card' by targeting tasks specifically.

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 a member should be notified about task updates. However, it does not explicitly contrast with related tools like 'remove_task_subscriber' or 'subscribe_card', nor does it mention when not to use it. The context is clear but lacks 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?

Beyond annotations (non-destructive write), the description discloses that notes will be hidden from the canvas and grouped under the stack, providing valuable behavioral context. 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?

Two sentences with no unnecessary words. It is front-loaded with the main action and includes the key effect.

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 4 required parameters, no output schema, and annotations, the description adequately covers the purpose and effect. It could mention prerequisites (e.g., stack must exist) or error conditions, but is generally 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%, so the baseline is 3. The description does not add additional parameter details beyond the schema, but it reinforces the 'one or more notes' concept aligning with the array type.

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 'add' and the resource 'notes to an existing stack', differentiating it from sibling tools like 'create_stack' or 'dissolve_stack'. It also explains the effect of adding 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 implies when to use this tool (adding notes to a stack) but does not provide explicit guidance on alternatives or when not to use it. It lacks distinctions from similar tools like 'add_comment' or 'create_note'.

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, destructiveHint=false, openWorldHint=false. The description adds behavioral context: it waits for the user's answer, the response type (channel notification from chat listener), and the three question types with their behaviors. 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 four sentences, front-loaded with the main purpose. It is clear and each sentence adds value, though it could be slightly more concise. Still 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 4 parameters, no output schema, and annotations, the description covers the workflow (ask, wait, receive notification) and explains the question types sufficiently. No obvious 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 description coverage is 100%, so baseline is 3. The description adds value by explaining the 'type' parameter options and the 'options' parameter usage, going beyond 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?

The description clearly states the verb ('ask a question'), resource ('card's AI chat'), and action ('wait for the user's answer'). It distinguishes from terminal by noting the user may only be monitoring card chat. It also lists the three question types explicitly.

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

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

The description provides explicit guidance to use this tool instead of asking in the terminal, and explains that the response arrives as a channel notification. It does not list when not to use or provide other alternatives, 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 adds important behavioral context beyond annotations: it deletes connected edges and notes irreversibility. This aligns with the destructiveHint annotation and provides clear understanding of side effects.

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 extremely concise—only two sentences—and front-loads the purpose. Every word is necessary, no redundancy.

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

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

For a delete tool with no output schema, the description covers key aspects: action, resource type, limit, and irreversibility. It could note whether the operation is atomic or handles partial failures, but remains largely 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% with descriptions for all three parameters. The description adds no extra meaning beyond the schema; it merely restates that multiple node IDs are deleted. Thus, minimal value added.

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

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

The description clearly states the action (delete), resource (canvas nodes such as cards/notes/stacks), and scope (many, up to 200) along with edges. It effectively distinguishes from sibling single-delete tools like delete_card or delete_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 includes a limit (Max 200 nodes) and warns it cannot be undone, helping the agent decide against misuse. However, it does not explicitly contrast when to use this batch tool versus individual deletion 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 already indicate the tool is not read-only and not destructive. The description adds value by specifying the input format (nodeId to {x,y}) and the 200-node limit, providing context beyond annotations about the operation's constraints.

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

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

The description is two sentences, front-loaded with the core purpose, followed by the key usage detail. No unnecessary words; 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?

Given the tool's simplicity and the absence of an output schema, the description covers the main aspects: operation type, target nodes, input format, and a critical limit. It could mention the return value or side effects, but it is mostly complete for a batch move.

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 a non-schema constraint ('Max 200 nodes per call') and clarifies the nested structure with a concrete example, enhancing understanding beyond the schema alone.

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

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

The description explicitly states the verb 'move', the resource 'canvas nodes (cards/notes/stacks)', and the scope 'many...in one call'. It distinguishes from the sibling tool 'move_node' by specifying batch capability and a maximum of 200 nodes.

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 moving multiple nodes in a single call with a max limit of 200, but it does not explicitly state when to use this over the single-node sibling 'move_node' or provide exclusions/alternatives. The guidance is present but implicit.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, which the description does not contradict. However, the description adds no additional behavioral context such as permissions required, side effects, or limitations 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 a single, concise sentence that efficiently communicates the tool's purpose. Every word is necessary.

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 creation tool with full schema coverage and no output schema, the description is sufficiently complete. It provides the core action, and annotations handle safety 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 description coverage is 100%, so the baseline is 3. The description adds no further meaning to parameters beyond what the input schema already specifies.

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 'Create a new calendar event' clearly states the action (create) and the resource (calendar event). It effectively distinguishes from sibling tools like calendar_delete_event and calendar_list_events.

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 events but provides no explicit guidance on when to use this tool versus alternatives (e.g., calendar_update_event for modifications). No exclusions or context-specific notes.

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 claims a destructive action (delete), but annotations set destructiveHint to false, creating a direct contradiction. No additional behavioral traits (e.g., irreversibility, confirmation requirements) are disclosed beyond the annotation conflict.

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, highly concise. It is front-loaded with the core action but lacks structural elements like bullet points or separate sections, though it does not waste 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?

With no output schema and no description of return values or side effects, the description is incomplete for a delete operation. The agent cannot infer what happens after deletion (e.g., success response, cascade effects, reversibility).

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

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

The input schema provides full descriptions for both parameters (workspaceId, eventId), so the description adds no extra semantic value. Baseline score of 3 applies as schema coverage is 100%.

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

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

The description clearly states the action (delete) and resource (calendar event). It is unambiguous and distinguishable from non-delete sibling tools, though it does not add extra context beyond the name.

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. There is no mention of prerequisites, edge cases, or situation-specific advice, leaving the agent without decision support.

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, which cover safety. The description adds minimal context beyond 'get details'; it does not mention the nature of the returned data, authentication needs, or any limitations. With annotations present, a 3 is appropriate for adding little beyond them.

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

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

The description is a single concise sentence with no wasted words. However, it could be slightly more informative while remaining concise, hence a 4 rather than 5.

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 (two required params, no output schema, no nested objects), the description is mostly complete for a straightforward get operation. It lacks details about the event structure returned, but that is not critical for a read-only tool with existing annotations.

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

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

The input schema provides 100% description coverage for both parameters ('Workspace ID' and 'Calendar event ID'). The description does not add further meaning beyond the schema, matching the baseline of 3.

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

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

The description clearly states the tool's purpose: 'Get details of a specific calendar event.' The verb 'get' and resource 'calendar event' are specific, and it distinguishes from sibling tools like calendar_list_events (list all) and calendar_create_event (create).

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 (when you need details of a single event) but provides no explicit guidance on when to use this tool versus alternatives or when not to use it. The sibling list is long but lacks differentiation cues.

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, so safety is covered. The description adds context about default 7-day range, but does not disclose other behaviors like pagination, ordering, or field selection. The schema provides param descriptions, so the tool description adds limited new behavioral insight.

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, clear sentence without redundancy. It is appropriately sized for a simple list tool, though it could include a brief note about return format.

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 the description should explain return values. It does not explicitly state that it returns a list of events or mention pagination or result limits. However, the param descriptions cover defaults, and the tool's purpose is straightforward.

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

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

Schema description coverage is 100%, so the tool description does not need to add parameter meaning. It mentions default time range (next 7 days) but that is already in the param descriptions. No additional parameter value is provided.

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 lists calendar events with a default time range. It distinguishes from calendar_get_event (single event) and other list tools by resource type. However, it does not explicitly mention workspace context, though the required param implies it.

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 on when to use this tool vs alternatives like calendar_get_event or other list tools. No mention of prerequisites, limitations, or when not to use.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the 'update' verb aligns with mutation. The description adds no further behavioral context (e.g., whether partial updates are allowed, error handling, or side effects). With annotations covering the safety profile, a score of 3 is appropriate.

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

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

The description is a single sentence with no superfluous words. It is front-loaded and directly communicates the tool's action. Every word earns its place.

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

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

Given the tool's moderate complexity (7 params, 2 required) and the presence of a thorough input schema, the description is adequate. No output schema exists, but the tool's purpose is straightforward. The openWorldHint annotation is noted, but the description could mention that only provided fields are updated. Still, it is sufficiently complete.

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

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

All 7 parameters are described in the input schema (100% coverage), so the description adds no additional meaning beyond what the schema provides. Per guidelines, baseline is 3 when schema coverage is high and description adds no param-specific details.

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

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

The description states 'Update an existing calendar event,' which is a clear verb+resource pair. It distinguishes from sibling tools like calendar_create_event, calendar_delete_event, calendar_get_event, and calendar_list_events by specifying 'update' instead of create, delete, get, or list.

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 indicates use for modifying existing events but provides no explicit guidance on when to use this tool versus siblings, such as when to create or delete events. No alternatives or 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context about 'recent chat messages' and the card's AI chat, which is consistent and goes beyond the annotations. No contradictory or additional behavioral traits needed.

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-loads the action, and every word adds value. No wasted text.

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 tool with well-defined parameters and annotations, the description covers the essential purpose and usage. No critical 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 clear parameter descriptions for cardId and limit. The description does not add extra meaning beyond the schema, so baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'Read' and resource 'recent chat messages from a card's AI chat', distinguishing it from siblings like 'ask_chat' and 'chat_respond'.

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

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

The description explicitly says it is 'useful for understanding context before responding to a chat message', providing clear when-to-use guidance. It does not explicitly mention when not to use or alternatives, which prevents a score of 5.

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

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

Description aligns with annotations (readOnlyHint=false, destructiveHint=false). Adds context about appearing in chat UI. No contradictory information, though side effects beyond UI are not mentioned.

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, front-loaded with the primary action, no filler. 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 tool with 2 required params and no output schema, the description covers the trigger and result adequately. Could mention visibility of response but not required.

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 covers both parameters with descriptions (100% coverage). Description adds no additional parameter information beyond what schema provides, earning the baseline 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 states the specific verb 'Send a response' and resource 'card's AI chat', and distinguishes from the sibling 'ask_chat' by noting the trigger 'when you receive a chat_message notification'.

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

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

Explicitly states when to use (upon chat_message notification) and implies not for initiating. Could benefit from explicitly naming the alternative tool 'ask_chat' but is otherwise 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 readOnlyHint=false and destructiveHint=false. The description adds behavioral context beyond annotations by revealing that one option (force-push) is destructive, and that the tool is asynchronous ('Wait for their reply before acting'). 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 extremely concise: two sentences that first state the tool's action and options, then give usage conditions. No redundant words; front-loaded with the key purpose.

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

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

Given the tool's simplicity (no output schema, single interaction pattern), the description is complete. It explains what the tool does, when to use it, and that it requires waiting for user input. 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%, so the description adds little beyond schema field descriptions. It does provide context that 'content' is a human-readable line and that 'payload' contains structured data, but this is already implied by 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 the tool renders a card to ask the user how to handle an existing GitHub repo name. It lists the specific options (use existing, create new, force-push) and distinguishes itself from siblings by its unique purpose of repo conflict resolution.

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

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

The description explicitly states when to use the tool: after detecting that the suggested name is taken via github_search_repos or github_get_file. It also instructs to wait for the user's reply. While it does not mention alternatives, the context is clear and sufficient for an AI agent.

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 non-read-only and non-destructive, so the description adds context about snapshotting metrics. However, it does not disclose idempotency or behavior if sprint already completed.

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?

Single sentence with 20 words, front-loaded with action and critical info. 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?

Core action and metrics listed, but lacks details on output, reversibility, or side effects. Adequate for a simple completion action but could be more thorough.

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 does not add any meaning beyond the schema-defined parameter descriptions. No improvement over 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 tool marks a sprint as completed and snapshots its metrics, distinguishing it from siblings like create_sprint or update_sprint. It uses specific verbs and resource reference.

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 on when to use vs alternatives. Does not mention prerequisites (e.g., sprint must be active) or when not to use.

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-read-only and non-destructive behavior. The description adds that it returns 'connected cards where the task can be moved next', which is useful behavioral context beyond annotations. It could mention side effects (e.g., whether task becomes immutable) but still adds value.

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, each serving a clear purpose: the first states the core action, the second describes the return value. No unnecessary words, and the information is 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 mutation tool with 2 parameters and no output schema, the description covers the essential purpose and return value. However, it could be more complete by mentioning what happens if the task is already done or if there are preconditions (e.g., task must be in a certain status). Still, it is sufficiently complete for most use 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?

The input schema has 100% coverage for both parameters (cardId and taskNumber). The description does not add any additional meaning or constraints beyond what the schema provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the action ('marks a task as done') and the resource ('task'). It also specifies the return value ('connected cards where the task can be moved next'), which distinguishes it from sibling tools like 'update_task' or 'restore_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 implies the tool should be used when wanting to complete a task, but it does not explicitly state when to use it versus alternatives like 'update_task' (to change status manually) or 'restore_task' (to undo completion). No exclusion criteria or prerequisites are given.

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, destructiveHint=false, and the description adds that the card is 'red, friction-heavy' and optionally requires re-typing a string. This provides behavioral context (UI, blocking) beyond what annotations convey, though it could be more explicit about blocking behavior or return value.

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

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

The description is two sentences, front-loaded with the main purpose and followed by an optional detail. It is concise but could be slightly more structured (e.g., bullet points for examples).

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 does not explain what happens after the user confirms (e.g., return value, next steps). Given no output schema, this gap may leave an agent unsure about the tool's behavior beyond rendering.

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 parameters. The description only adds that requireType is optional, which is already in the schema. No additional meaning 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?

The description clearly states the tool renders a confirmation card before irreversible actions, with specific examples (delete repo, drop database, force-push, wipe workspace). It distinguishes itself from sibling tools like delete_board by being a confirmation step, not the action itself.

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

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

The description explicitly says to use the tool 'BEFORE any irreversible action', providing clear context. It lacks explicit 'when not to use' or alternatives, but the usage is well-defined.

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 are limited (readOnlyHint false, destructiveHint false). The description adds return value and default visibility but lacks details on side effects, permissions, or rate limits.

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

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

Three clear sentences with no fluff, efficiently conveying key 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?

Describes return value and default visibility, which is good for a creation tool. Could mention creation of default columns, but overall adequate.

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 schema already describes parameters. Description adds context about visibility default but does not enhance meaning for each parameter beyond what schema 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 creates a board in the workspace, returns the boardId, and notes default visibility. It distinguishes from siblings like update_board or delete_board.

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 or alternatives. The description implies use for creation but does not compare to other tools or provide 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?

The annotations already indicate readOnlyHint=false and destructiveHint=false, so the description's statement that it creates a card adds no new behavioral insight. It does disclose the return value (cardId/nodeId) but does not cover permissions, failure modes, or side effects.

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

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

The description is two sentences long, each serving a clear purpose: the first states the primary action, the second adds useful context about the return value. No waste.

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

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

Given the absence of an output schema, the description usefully mentions the returned cardId/nodeId and its potential use. However, it could be more complete by clarifying that a 'card' here is a column and explaining optional parameters' default behaviors.

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

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

All 10 parameters have descriptions in the schema (100% coverage), so the description adds no extra meaning beyond the schema. The description does not explain the relationship between card and column or how icon, color, and position affect the card.

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 new kanban card (column) on a board, specifying the verb and resource. It differentiates from siblings like create_task or create_note by naming the object as a card/column.

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 provide explicit guidance on when to use this tool versus alternatives like create_task, create_note, or update_card. It only hints that the returned ID can be used with subscribe_card or read_card, which is implied 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 show readOnlyHint=false and destructiveHint=false, consistent with the description's mention of 'connect' (a mutation). The description adds that edges are directional and handles are optional, which is helpful but not extensive. 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?

Two concise sentences front-load the main action and optional features. Every sentence adds value with no waste, achieving effective communication.

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 creation tool with 6 parameters and no output schema, the description is adequate. It covers the core action and optional handles but omits potential edge cases (e.g., duplicate edges, invalid node IDs). Still, it provides sufficient context for typical use.

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

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

Schema coverage is 100%, so parameters are already documented. The description adds that handles specify 'which side of each node the edge connects to,' matching the enum values. This adds minimal extra meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: 'Connect two canvas nodes (cards or notes) with a directional edge.' It specifies the verb (connect), resource (nodes), and result (directional edge), distinguishing it from sibling tools like delete_edge or list_edges.

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 (to create an edge) but provides no explicit guidance on when to use this tool versus alternatives. No exclusions or when-not advice are given, leaving the agent to infer context.

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 adds that markdown is supported and auto-connection via edge occurs. No contradictions. Slightly more detail on side effects could elevate, but sufficient.

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, front-loaded with core action, no wasted words. Extremely concise.

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

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

For a creation tool with no output schema, the description covers key behavioral aspects (markdown, auto-connect). Could mention return value or confirmation, but not critical. Annotations are minimal but consistent.

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 6 parameters, so baseline is 3. Description adds extra context only for 'nearNodeId' beyond schema, but not enough to raise score.

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

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

The description explicitly states 'Create a new note on the canvas board' with specific verb and resource, and distinguishes from siblings like 'create_card' by mentioning markdown support and auto-connect feature.

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 guidance on when to use 'nearNodeId' for placement and auto-connection. It could be more explicit about when to choose this tool over alternatives like 'create_card', 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?

Annotations indicate non-read-only, non-destructive, non-open-world. The description adds constraints: max 90 days duration and default status PLANNING. This provides 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?

Three sentences, front-loaded with core purpose, no unnecessary words. Efficiently conveys all key points.

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 all essential aspects: creation action, required parameters implied, constraints (duration, default). Missing explicit mention of boardId but implied by 'on a board'. Sufficient for a creation tool with complete schema descriptions.

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%. Description adds explicit date format (YYYY-MM-DD), notes optional goal, default status, and max duration – meaningful additions that clarify usage 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 uses specific verb 'create' and resource 'sprint', lists key parameters (name, startDate, endDate, goal), and includes default status and duration limit, clearly distinguishing it from siblings like complete_sprint or update_sprint.

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 vs alternatives (e.g., update_sprint, list_sprints). Usage is implied for starting a new sprint, but no exclusions or comparison provided.

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

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

Annotations already indicate mutation (readOnlyHint=false). The description adds valuable context beyond annotations: 'Their edges are removed' and 'Minimum 2 notes required'. This informs the agent of specific side effects 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?

Two sentences front-load the purpose and key details. 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 tool with clear annotations and no output schema, the description covers purpose, behavior, constraints, and side effects completely. No gaps remain.

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

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

Schema coverage is 100%, so parameters are already well-documented. The description reiterates the minimum of 2 notes, which aligns with noteIds schema, but adds no new semantic meaning beyond what the schema 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 action ('Group multiple notes into a stack') and its visual effect on the canvas. It also distinguishes from sibling tools like 'add_to_stack' or 'dissolve_stack' by outlining the specific behavior (edges removed, minimum 2 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 implies usage when collapsing notes but does not explicitly state when to prefer this tool over siblings like 'add_to_stack' or 'dissolve_stack'. No exclusion criteria or alternatives 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?

Annotations already indicate that the tool is not read-only. The description adds that it returns the created task with an auto-assigned number, which is useful but does not disclose other behaviors like permissions or side effects.

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

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

The description is two sentences, front-loaded with the core purpose, and contains no wasted words. It is concise and well-structured.

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 13 parameters and no output schema, the description is minimal. It explains the return value but omits details like prerequisites, error conditions, or the format of the auto-assigned number. Schema coverage helps, but the description could be more complete for such a complex 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 input schema has 100% description coverage, so the baseline is 3. The description does not add meaning beyond what the schema already provides for individual 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 clearly states the action ('creates'), the resource ('a new task'), and the location ('in the specified card'). It distinguishes creation from sibling tools like update_task or delete_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 guidance is provided on when to use this tool versus alternatives such as add_subtask or other creation tools. The description simply states what the tool does without context for selection.

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 critical behavioral context beyond annotations: it confirms permanence and clarifies what gets destroyed (board and its contents). This complements the destructiveHint=true annotation without 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?

The description is two concise sentences that efficiently communicate the core action, scope, and constraints 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?

For a simple destructive tool with two parameters and clear annotations, the description fully covers the purpose, permissions, and consequences. No additional details are needed.

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 documented; the description adds no extra information about the parameters 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 specific action ('permanently delete a board') and distinguishes from sibling tools like delete_card or delete_note by noting that it deletes all contents (cards/notes/edges).

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

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

It specifies that only the owner can perform this action and warns it cannot be undone, providing clear usage constraints. However, it does not explicitly contrast with alternative delete tools or state when to prefer this over other deletion methods.

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

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

Annotations already mark destructiveHint=true; the description adds value by specifying cascade deletion of edges and tasks and irreversibility. 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?

Two sentences, zero wasted words, front-loaded with core action. Highly concise yet 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 the destructive nature and cascade effects, the description adequately covers what gets deleted. Could mention if any confirmation is required, but 'Cannot be undone' suffices. No output schema needed.

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 no extra parameter semantics beyond the schema, so baseline is appropriate.

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

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

The description clearly states the tool's purpose: permanently delete a card, its connected edges, and its tasks. It distinguishes from siblings like update_card or create_card.

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 when to use (to delete a card) but does not explicitly state when not to use or mention alternatives like delete_board or delete_task. Context is clear but lacks 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?

The description adds behavioral context beyond annotations: it specifies that deletion is permanent and that only the author or workspace owner can perform it. Annotations only indicate destructive nature, so description provides valuable extra details about authorization and irreversibility.

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 extremely concise: two sentences with no unnecessary words. Every phrase ('permanently delete', 'Author or workspace owner only') adds meaningful information without redundancy.

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

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

Given the tool's simplicity (2 required parameters, no output schema), the description covers essential aspects: action, permanence, and authorization. Slightly lacking explicit mention of return behavior, but for a destructive delete, it is adequate.

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 (workspaceId, commentId) described. The description does not add additional semantic meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool's action ('permanently delete a comment') and its resource, making it unambiguous. It also distinguishes from siblings like 'update_comment' by emphasizing permanence and authorization constraints.

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 a key usage condition ('Author or workspace owner only'), which helps agents determine if they can invoke it. However, it lacks explicit guidance on when to prefer this over alternatives like 'edit/remove' or when deletion is appropriate.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds minimal context beyond 'remove a connection'. It does not contradict annotations, but adds no additional behavioral details like irreversibility or permission requirements.

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

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

The description is a single sentence of 12 words, front-loaded with the action and resource. Every word is necessary and there is no redundancy.

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

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

For a simple delete operation with three straightforward parameters and no output schema, the description is adequate. It could mention that the deletion is irreversible, but annotations already signal destructiveness.

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% description coverage for the three parameters, so the baseline is 3. The description does not add any extra 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 it removes a connection between two canvas nodes. The verb 'remove' and resource 'edge' are specific. It distinguishes from sibling tools like create_edge, list_edges, and batch_delete_nodes by being a single edge deletion.

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

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

The description implies it is for removing a single edge from a canvas, but does not explicitly state when to use it versus other deletion tools like batch_delete_nodes. However, given the specificity of the tool name and description, it 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?

Adds beyond annotations by specifying permanent deletion from both storage and Firestore record, and user eligibility. Annotations already mark destructive=true, but description gives more detail.

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

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

Single sentence of 14 words, perfectly front-loaded with action and scope. No unnecessary content.

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 all necessary context: effect (permanent deletion), scope (storage and record), and authorization. No output schema needed for this simple action.

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. The description does not add further parameter meaning, so baseline 3 applies.

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

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

The description clearly states the action (permanently delete) and resource (file from storage and Firestore record), distinguishing it from sibling tools like 'delete_note' or 'delete_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?

Specifies access restriction ('Uploader or workspace owner only'), providing clear context for when to use. Does not explicitly state alternatives for unauthorized users, but the constraint 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 value beyond the annotations by specifying that edges connected to the note are also permanently deleted. The annotations already indicate destructive nature (destructiveHint: true), and the description aligns with that while providing additional 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 a single, focused sentence of 13 words. It is front-loaded with the action and result, with no wasted words or filler.

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

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

For a simple delete operation, the description adequately explains the effect (permanent deletion of note and edges). No output schema exists, but the return value is typically implicit for deletions. Complements the annotations well.

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

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

All three parameters have schema descriptions (100% coverage), so the description does not add meaning beyond what the schema provides. Baseline score of 3 is appropriate.

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

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

The name, title, and description clearly state 'Delete Note' and specify the action as 'Permanently delete a note'. It identifies the resource (note) and distinguishes from sibling delete tools (e.g., delete_board, delete_card) by adding 'along with any edges connected to it'.

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 is provided on when to use this tool versus alternatives (e.g., archive or remove from view). There is no mention of prerequisites or when not to use it. The context hints at use for permanent removal, but lacks exclusions or alternative references.

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

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

Annotations already indicate destructiveHint=true, but the description adds 'permanently' and specifies that the caller must be the recipient, providing useful behavioral context beyond annotations. 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?

Two sentences, front-loaded with the action, no wasted words. Every sentence earns its place.

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

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

The tool is simple (delete a notification). Description covers what it does, permanence, and access condition. No output schema needed; return value is implied. Complete for the task.

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% (both parameters have descriptions), so baseline is 3. The description does not add extra meaning to parameters beyond what the schema 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 verb 'permanently delete' and the resource 'notification', with the condition 'Caller must be the recipient.' This differentiates it from sibling tools like mark_notification_read, which only marks as read, and list_notifications.

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 when to use (to permanently delete a notification) and when not (if you just want to mark as read, use mark_notification_read), but lacks an explicit alternative. The presence of mark_notification_read as a sibling tool helps, but the description could be more explicit.

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

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

Annotations already indicate destructive behavior. Description adds context that deletion is permanent and affects a single task. 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?

Two sentences, no wasted words. The purpose is front-loaded, and the alternative is succinctly provided.

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?

Describes the core action well but does not mention return value or confirmation. For a delete tool, this is generally acceptable but could be slightly improved.

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%, and the description adds no additional 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?

Clearly states the tool 'permanently delete a single task' with a specific verb and resource. Distinguishes from sibling 'update_task' by noting the alternative for non-destructive removal.

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

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

Explicitly says when to use (permanent deletion) and when not to ('to remove without losing history, prefer update_task with archived=true'), providing an alternative 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?

Description adds 'permanently delete' and authorization details beyond annotations (destructiveHint: true). No contradiction; reinforces irreversibility and access restrictions.

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 succinct sentences: action then authorization. No unnecessary words or 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?

Adequate for a simple delete tool with two required params and no output schema. Covers permanence and authorization, though success/error behavior not mentioned.

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 covers both parameters with descriptions (100% coverage). Description adds no extra parameter details 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 clearly states 'Permanently delete a worklog entry' with specific verb and resource. Distinguishes from sibling delete tools by targeting worklog specifically.

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?

Description provides authorization context ('Author or workspace owner only') but does not specify when to use vs alternatives like update_worklog or when not to use.

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 destructiveHint=true and readOnlyHint=false. The description adds that the stack node is deleted and notes are restored, providing behavioral context beyond annotations. 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?

Two concise sentences that are front-loaded with the action and effect. No 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?

The tool has no output schema, but the description sufficiently explains the effect. Given the three required parameters and the destructive nature, the description is complete. Could mention irreversibility, but it's implied by 'dissolve' and destructiveHint.

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 three parameters. The description does not add extra meaning beyond what the schema provides, so 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?

Clearly states it dissolves a stack, restoring notes as independent nodes and deleting the stack node. The verb 'dissolve' and resource 'stack' are specific, and it distinguishes from siblings like create_stack and add_to_stack.

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 outcome but does not explicitly state when to use or alternatives. However, the context is clear as it is the reverse of creating or adding to a stack.

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-destructive mutation (readOnlyHint=false, destructiveHint=false). The description adds only 'Create', which is already implied. No additional behaviors (e.g., workspace requirement, duplicate handling, rate limits) are disclosed.

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 7-word sentence, extremely concise and front-loaded. However, it is so brief that it sacrifices essential context; every word earns its place but a bit more structure would improve 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 3 parameters (2 required), no output schema, and many sibling tools, the description provides minimal context. It omits the optional content parameter, return value, and any workspace or permission context, making it insufficient for complete understanding.

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% (all parameters have descriptions), so the baseline is 3. The description adds no extra meaning about parameters, but the schema already handles semantics.

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

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

The description 'Create a new Google Docs document' uses a specific verb ('create') and resource ('Google Docs document'), clearly distinguishing it from siblings like 'drive_create_folder' or 'drive_create_sheet'.

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

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no when-not-to-use conditions. It is a single sentence without any contextual advice.

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 mutation (readOnlyHint=false), but description adds no extra context about required permissions, naming constraints, or behavior when folder name conflicts exist. Lacks behavioral depth.

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 single sentence. While not wasteful, it is overly brief and lacks structure to highlight key aspects. Could be improved with a brief usage note.

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 and simplicity, the description should explain that workspaceId is required and parentId is optional. It does not mention default behavior when parentId is omitted (creates in root). Incomplete overall.

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 covers all parameters with descriptions (100% coverage). Description adds no additional semantics beyond the schema, which is acceptable given schema completeness. However, it doesn't clarify parentId's role as optional.

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 the action (create) and resource (folder in Google Drive). It is distinct from sibling tools like drive_create_doc or drive_create_sheet, but could be more specific about the scope (e.g., within a workspace).

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 on when to use this tool versus alternatives. For instance, it doesn't clarify that workspaceId is necessary or that parentId is optional for root folders.

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 it is a write operation (readOnlyHint=false) and creates new entities (openWorldHint=true). The description merely restates 'create new,' adding no behavioral context beyond annotations, such as permissions required or side effects.

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?

Single, front-loaded sentence of 6 words. No extraneous information; every word earns its place.

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

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

No output schema, and the description does not mention what the tool returns (e.g., spreadsheet URL or ID). For a creation tool, this is incomplete; the agent cannot know the type of response.

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 (workspaceId and title). The description adds no additional meaning; it simply restates the tool's purpose without elaborating on parameter roles.

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 'Create a new Google Sheets spreadsheet' uses a specific verb ('create') and resource ('Google Sheets spreadsheet'), clearly differentiating from siblings like drive_create_doc or drive_create_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?

No guidance on when to use this tool versus alternatives (e.g., drive_create_doc for documents). No prerequisites or conditions for use 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?

Annotation destructiveHint=false contradicts the description which indicates a destructive operation. This creates confusion; no additional behavioral context provided (e.g., irreversibility, permission requirements).

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?

Single sentence, no redundant words, directly states 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?

Lacks important context such as deletion being permanent, file must exist, or effects on shared files. No output schema documented.

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 two params (workspaceId, fileId) with basic descriptions. Description adds no further meaning 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?

Description clearly states the action ('Delete') and resource ('a file or folder from Google Drive'), distinguishing it from other delete tools among siblings (e.g., delete_board, delete_file).

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 on when to use this tool versus alternatives like delete_file (generic) or delete_board. No mention of prerequisites, permanence, or confirmation steps.

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. Description adds that it returns metadata and embed URL, which aligns with read-only behavior. No contradictions, but minimal additional behavioral insight.

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?

Single sentence, front-loaded with the action. No wasted words. Highly 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?

The tool is simple and the description covers the basic purpose. Without an output schema, it could elaborate on the metadata fields, but it's adequate for a straightforward get 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% with descriptions for both parameters. The description does not add any parameter-specific meaning beyond what the schema provides, 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?

The description 'Get file metadata and embed URL' clearly states a specific verb ('Get') and resource ('file metadata and embed URL'), distinguishing it from sibling tools like drive_delete_file or drive_search_files.

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 on when to use this tool versus alternatives (e.g., drive_search_files or drive_get_file is for specific files). No exclusions or context provided.

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

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

Annotations already indicate non-readOnly and non-destructive. The description adds no behavioral context (e.g., permissions, side effects) beyond stating it moves the file.

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?

Single short sentence, no fluff. However, it could be slightly more informative while remaining concise.

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

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

For a simple 3-parameter tool with no output schema, the description is adequate but lacks details on return values or behavior, which 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 covers all 3 parameters with descriptions (workspaceId, fileId, targetFolderId). The description does not add extra meaning beyond what the schema provides, so baseline 3 applies.

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

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

The description clearly states the action (move), resource (file), and destination (different folder). This distinguishes it from sibling tools like drive_delete_file or drive_get_file.

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 moving single files but provides no guidance on when to use alternatives like batch_move_nodes or move_node, nor any 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, so the description need not restate those. The description adds no behavioral context (e.g., result limits, pagination), but the annotation coverage is sufficient.

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 conveys the purpose without any extraneous words. It is appropriately 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?

While the description and annotations provide a basic understanding, the tool lacks an output schema and the description does not explain return values or behavior. For a search tool, this is adequate but not fully comprehensive.

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

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

Schema description coverage is 100%, and the description adds no additional meaning beyond the schema descriptions. Both parameters are adequately documented 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 'Search files in the connected Google Drive,' which specifies the action and resource. However, it does not differentiate from sibling tools like 'list_files' or 'drive_get_file' that may also list files.

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 such as 'list_files' or 'drive_get_file.' No prerequisites, limitations, or preferred contexts 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 annotations indicating mutation (readOnlyHint=false) and possible side effects (openWorldHint=true), the description adds no behavioral context. It does not disclose what happens if only required params are provided, or if other properties remain unchanged.

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

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

The description is a single, front-loaded sentence that directly conveys the tool's action. While it could be slightly more concise (e.g., 'Rename or update file description'), it has 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?

The description lacks information about return values (no output schema), and does not explain the role of required parameters (workspaceId, fileId) beyond being identifiers. The tool updates files, but there is no mention of error conditions or side effects, leaving gaps for a non-expert agent.

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 basic descriptions for each parameter. The description reiterates 'name' and 'description' purposes but adds no extra constraints, formats, or examples. Baseline of 3 is appropriate as the schema already covers the parameter meanings.

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 renames a file or updates its description. This uses specific verbs (rename, update) and defines the resource (file), effectively distinguishing it from sibling tools like drive_delete_file or drive_move_file.

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 on when to use this tool versus alternatives like drive_move_file or drive_get_file. It does not provide context for choosing this over other file operations, nor does it mention prerequisites or conditions.

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, and openWorldHint=true. The description adds no additional behavioral context beyond what annotations and name imply, such as pagination, ordering, or response format.

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, clear sentence with no unnecessary words. It efficiently conveys 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?

For a simple read-only tool with two required parameters and no output schema, the description is minimally adequate but lacks details about the return value structure, pagination, or any caveats. It does not fully compensate for the absence of an 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%, with both parameters already having descriptions in the schema. The tool description does not add extra meaning beyond the schema, so 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 'Get comments on a Figma file' clearly states the verb 'Get' and the resource 'comments on a Figma file', distinguishing it from sibling tools like figma_post_comment and list_comments.

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

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

The description provides no guidance on when to use this tool versus alternatives such as list_comments (generic) or figma_post_comment. No explicit when-to-use or when-not-to-use conditions are given.

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, and openWorldHint. The description adds specifics about the returned fields (name, thumbnail, pages), which enriches the behavioral context without contradicting 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 a single sentence that is front-loaded with the action and resource, no filler words, and efficiently communicates the tool's 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?

For a simple read-only tool with two parameters and no output schema, the description adequately specifies the returned metadata. It could be improved by mentioning if pagination or other details exist, but given the low complexity, it is sufficient.

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

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

Schema coverage is 100% with descriptions for both parameters (workspaceId, fileKeyOrUrl). The description does not add additional meaning beyond what the schema already provides, so 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 the verb 'Get', the resource 'Figma file', and specifies the returned metadata: name, thumbnail, pages. It distinguishes from sibling tools like figma_get_comments and figma_post_comment.

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 a read-only retrieval context but provides no explicit when-to-use or when-not-to-use guidance, nor mentions alternatives. Usage is clear from the tool name and annotations but lacks explicit 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?

The description confirms the tool creates a comment (non-read-only, non-destructive), which aligns with annotations. However, it adds no further behavioral context such as authentication requirements, side effects, or response behavior, relying entirely on 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 a single, clear sentence with no unnecessary words. It efficiently communicates the core purpose, making excellent use of conciseness.

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 three-parameter tool with no output schema, the description is adequate but minimal. It lacks details like return value or success confirmation, though the schema and annotations partially compensate.

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

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

The schema already provides 100% coverage for all three parameters. The description adds no additional information about parameter semantics, so it meets the baseline but does not 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 the action ('Post a comment') and the target resource ('on a Figma file'), making the purpose immediately understandable. However, it does not explicitly differentiate itself from the sibling tool 'add_comment', which might cause confusion.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'add_comment' or 'figma_get_comments'. There is no mention of prerequisites, context, 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 indicate readOnlyHint=true and destructiveHint=false. The description adds the specific return format, including the { active: false } case, which is valuable behavioral information 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 a single sentence that is front-loaded and efficient. Every word serves a purpose with no wasted text.

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 the return value. It could mention potential error conditions (e.g., invalid boardId), but it is largely complete for a simple read 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%, so the description does not need to add parameter details. It does not provide additional meaning beyond the schema, so baseline score of 3 is appropriate.

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

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

The description clearly states the tool returns the active sprint for a board, with a specific fallback value. It distinguishes itself from sibling tools like 'list_sprints' by focusing on the current active sprint.

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 when to use (when needing the active sprint), but does not explicitly mention when not to use or provide alternatives. However, the context from sibling tools makes the usage 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 already indicate readOnlyHint=true and destructiveHint=false. The description adds the key behavioral detail that the tool returns 'active=false' if no timer is running, which is not inferable from annotations alone.

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: first states purpose, second provides parameter guidance and expected return. No extraneous information, every sentence earns its place.

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

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

For a simple read tool with no output schema, the description covers purpose, parameter nuances, and the return state when no timer runs. It is fully adequate given the tool's complexity and the absence of sibling overlap.

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 both parameters. The description adds value by explaining the effect of omitting uid, which goes beyond the schema's 'defaults to caller' note.

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 tool reads the currently-running timer, specifies the resource ('timer') and the verb ('read'). It also distinguishes the parameter usage for personal vs. other members' timers, setting it apart from siblings which are mostly unrelated.

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

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

Provides explicit guidance on when to omit uid (to read own timer) and implies the tool is for checking active timers. While no direct alternatives are named, the context is clear given the sibling list contains no other timer-specific 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 already declare readOnlyHint=true and destructiveHint=false, so the read-only behavior is known. The description adds that it returns a 'full form definition' with specific fields, which is consistent but does not provide additional behavioral context beyond the annotations. No contradiction exists.

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

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

The description is a single sentence of 9 words, front-loading the verb 'Read' and the resource 'full form definition'. Every word is informative, with no redundancy or unnecessary elaboration. It is an exemplary model of conciseness.

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 operation with two required parameters and no output schema, the description adequately states the function and return fields. However, it could be more complete by noting that the output is an object (implied) or mentioning potential error scenarios (e.g., invalid formId). The absence of significant gaps keeps the score above average.

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

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

The input schema has 100% description coverage with minimal descriptions ('Workspace ID', 'Form ID'). The tool description does not add any further meaning or example values for these parameters. Since explanation coverage is high, a baseline of 3 is appropriate; the description does not enhance parameter understanding.

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

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

The description clearly identifies the tool as a read operation ('Read') for retrieving the full form definition, specifying the returned content: title, fields, settings, submissionCount. This distinguishes it from sibling tools like list_forms (which likely lists forms without full details) and other mutation 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 does not explicitly state when to use this tool over alternatives, such as list_forms or other read tools. While the purpose is clear, the lack of usage context or exclusion criteria leaves room for ambiguity. A mention of when to prefer get_form over list_forms would improve this dimension.

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. The description adds specific fields returned, which is useful, but does not disclose other behavioral traits like permissions or completeness of returned preferences.

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 directly states the tool's purpose and lists the returned fields, with no unnecessary content.

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 operation with one parameter and low complexity, the description provides sufficient context alongside annotations, though it could clarify if it returns all preferences or only the listed ones.

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 sole parameter workspaceId has a description in the schema (100% coverage), and the tool description adds no additional meaning beyond what the schema 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 it reads the caller's own preferences and lists specific fields (timezone, emailNotifications, canvasSettings), distinguishing it from write tools like update_user_preferences.

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 needing the caller's preferences but provides no explicit guidance on when to use this tool versus alternatives (e.g., get_workspace_settings) or when not to use it.

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, so the description's 'Read' aligns; no additional behavioral details are provided 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?

Single, efficient sentence with no wasted words; purpose is 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-by-ID operation with no output schema, the description sufficiently sets expectations; could mention return object but not essential.

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

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

Schema has 100% coverage with clear descriptions for both parameters; the description adds no extra 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?

Description states verb 'Read' and resource 'worklog entry by ID', clearly distinguishing from list (multiple) and delete/update 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?

Implies usage when a specific worklog ID is known; no explicit alternatives but context from sibling names suggests listing or mutation 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 already declare readOnlyHint=true and destructiveHint=false. The description adds specific return fields but does not disclose error behavior or conditions like workspace existence. The annotations carry the safety information.

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, efficient sentence that lists the returned fields. No unnecessary words or redundancy.

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

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

Given the low complexity (1 param, read-only, no output schema), the description is adequate. It specifies the returned settings. Could be slightly more explicit about whether this is all settings or a subset, but sufficient for a simple read.

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

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

The input schema fully describes the workspaceId parameter (100% coverage). The description focuses on return values and adds no further meaning to the parameter, so 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 uses the verb 'Read' and explicitly lists the workspace fields (name, timezone, currency, hoursPerDay, plan, storage usage). This clearly distinguishes it from sibling tools like update_workspace_settings which modify settings.

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 purpose is clear, but there is no explicit guidance on when to use this tool versus alternatives or any exclusions. The straightforward read operation and sibling names (e.g., update_workspace_settings) imply usage context.

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 the action is mutable (readOnlyHint=false) and not destructive (destructiveHint=false). Description adds no 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?

One short sentence is efficient, but could include a brief note on effects.

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 and no description of return value or side effects; adequate for a simple action but lacks 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 covers 100% of parameters with descriptions; the tool description does not add further meaning 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 uses a specific verb 'Close' and resource 'GitHub issue', clearly distinguishing it from sibling tools like github_close_pr.

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 on when to use this tool versus alternatives; no mention of prerequisites or context.

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 (write operation) and destructiveHint=false. The description adds value by clarifying it does not involve merging, but it doesn't mention side effects like notifications or that the PR can be reopened. It adequately supplements 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?

A single sentence that is concise and front-loaded. Every word is necessary, with no extraneous 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?

For a simple action with full schema coverage and no output schema, the description is sufficient. It could mention that closing does not affect the branch, but the operation is straightforward. Overall, it is contextually adequate.

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 parameters (workspaceId, repo, pullNumber). The tool description adds no further meaning beyond what the schema already provides. Baseline score is appropriate.

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

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

The description clearly states the action (close) and the resource (pull request). It also distinguishes from merging by explicitly saying 'without merging', which is a key differentiator from the sibling tool github_merge_pr.

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 tells when to use this tool: when you want to close a PR without merging. It effectively distinguishes from merge, but lacks explicit guidance on when not to use it or scenarios like abandoning a PR.

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?

While annotations indicate this is a non-destructive write operation with potential external side effects (openWorldHint), the description adds no additional behavioral context such as permission requirements, side effects like triggering CI, or error conditions. It merely restates the action implied by the annotations.

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

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

The description is a single, concise sentence that immediately conveys the core functionality. Every word is essential, and there is no redundant or extraneous 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?

Given the tool's simplicity and full schema coverage, the description covers the basic purpose. However, it lacks details about the result (e.g., the created branch reference), error handling, or post-creation effects, which would be helpful for completeness. It is minimally adequate but not thorough.

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 provides descriptions for all 4 parameters (100% coverage), so the description does not need to elaborate on parameter meaning. The baseline of 3 is appropriate as the description adds no extra semantic value beyond what the schema offers.

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

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

The description clearly states the action ('Create') and resource ('a new branch') with the source context ('from an existing ref'), making the tool's purpose unambiguous. It effectively distinguishes itself from sibling tools like github_create_issue or github_create_pr.

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

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

The description provides no guidance on when to use this tool over alternatives (e.g., checking out a branch locally) or when not to use it. It lacks any context about prerequisites, typical scenarios, or prohibitions, leaving the agent to infer usage solely from the name and parameters.

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