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

ReadOnlyHint annotation already covers the read-only nature; the description adds the endpoint but no additional behavioral details like error cases 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?

Two short sentences, though the second sentence adds minimal value; overall 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?

Simple get operation with an output schema present, so the description is sufficient without explaining return values; it adequately covers the essential 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?

The schema fully describes folder_id, and the description adds no extra parameter semantics; baseline 3 applies due to high schema coverage.

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

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

Clear and specific verb 'Get' with resource 'folder details' by ID, and it distinguishes from other get_* tools for different resources.

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 when-to-use or alternative guidance, but it is implied that this tool is for fetching a folder when you have its ID; lacks mention of 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 readOnlyHint=true, and the description adds useful behavioral context by specifying that the page body is returned as readable HTML in body_html. This goes beyond the structured annotation without contradicting it.

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

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

The description is compact and front-loaded: purpose first, usage condition second, return format third. Every sentence serves a distinct function and there is no unnecessary wording.

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

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

For a simple read-only lookup tool with one fully documented parameter and an output schema, the description covers purpose, usage, and return behavior. Nothing essential is missing for an agent to invoke it correctly.

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

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

The schema fully documents page_id as 'The unique Productive page identifier' with 100% coverage, so the description does not need to add much. It does not introduce additional parameter meaning beyond what the schema already provides, matching the 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 uses a specific verb ('Get') with a clear resource ('specific page/document by ID') and distinguishes itself by emphasizing 'full content body' versus metadata or titles. This makes it easy for an agent to tell it apart from list_pages and other sibling 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 explicitly states when to use it: when the full content body of a specific page is needed, and clarifies that it is not for metadata or titles. It does not name specific alternative tools or provide explicit exclusions, but the usage 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 context about the returned fields (name, email, role, title, timestamps, custom fields, avatar), which is beyond the readOnlyHint annotation. However, it does not disclose any potential constraints or side effects, but since annotations already indicate safe read operation, this is adequate.

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: one lead sentence for purpose, one for usage guidelines, and a bullet list of returns. No extraneous information; every sentence adds value. Front-loaded with 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?

Given the tool is a simple read-by-ID with one required parameter, an output schema, and readOnlyHint annotation, the description is fully complete. It explains what fields are returned and when to use it, leaving no gaps for an AI 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?

The input schema has 100% coverage for its single parameter (person_id), and the description adds no additional semantic details beyond stating it is 'by ID'. Baseline score of 3 is appropriate as the schema already provides sufficient information.

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

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

The description clearly states the tool retrieves detailed information about a specific team member by ID, using a specific verb ('Get') and resource ('person'). It distinguishes from the sibling tool 'list_people' by specifying that 'get_person' is for a single person while 'list_people' is for browsing multiple.

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 this tool ('when you need detailed information about a specific person') and when to use an alternative ('Use list_people when you need to browse or search multiple people'), providing clear usage boundaries.

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, but the description adds valuable behavioral detail beyond that: comment ordering and limiting via comment_limit, todo truncation with todos_truncated and todos_note, and attachment results limited to id and filename. This gives the agent an accurate picture of response behavior without needing to guess.

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

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

The description is front-loaded with the operation and then uses scannable bullets to enumerate return categories. Every line adds distinct information about task details, time tracking, todos, comments, or attachments. There is no filler or redundancy.

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

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

The description is complete for correct invocation: it specifies the required parameter format, the optional limit behavior, the return categories, and the truncation signals. The read-only annotation covers safety, and the existence of an output schema further reduces the burden. Nothing necessary for correct use is missing.

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 extra meaning by clarifying that task_id is an internal Productive identifier with a concrete example, and by explaining that comment_limit controls how many most recent comments are returned. It avoids merely repeating 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 states a specific verb and resource: 'Get detailed task information by its internal task ID.' It clearly distinguishes this from sibling tools like list_tasks (which lists many tasks) and get_task_history (which returns history rather than current task details). The example ID anchors the exact input expected.

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 usage context is implied: call this tool when you already have an internal task ID and need full details for that single task. However, the description does not explicitly mention alternatives or when not to use it, such as using quick_search or list_tasks to first locate the task ID. No exclusions or alternative routing are provided.

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

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

Annotations already declare readOnlyHint=true, indicating safe read-only behavior. The description goes beyond by detailing the returned data categories (status history, assignment history, etc.) and the time range parameter, adding valuable 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 well-structured with bullet points and clear examples, conveying essential information without redundancy. Every sentence adds value, and the format facilitates quick understanding.

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

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

Given the presence of an output schema, the description need not detail return values. It covers the main use case, parameters, and expected categories of history. It is nearly complete, though it could mention any limitations or pagination behavior for full completeness.

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

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

Schema description coverage is 100%, so the schema already explains both parameters (task_id and hours). The description does not add new semantic meaning beyond what the schema provides, though examples reinforce usage. Meets baseline for high schema coverage.

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

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

The description clearly states the tool gets comprehensive history for a task, with specific verb 'Get' and resource 'history for a specific task'. It distinguishes from sibling tools like get_task (task details) and list_tasks (list tasks) by focusing on historical data.

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

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

The description implies usage for retrieving task history and provides examples showing how to specify time range. However, it does not explicitly state when not to use it or mention alternatives, leaving room for improvement.

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

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

The description discloses detailed return fields (checkbox text, parent task, assignee, due date, time estimates, comments, attachments) which goes beyond the readOnlyHint annotation. No contradiction with annotations.

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

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

The description is concise: a single-sentence purpose, a one-line usage guideline, and a bullet list of returns. Every sentence adds value, no fluff.

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

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

Given the simple input (one parameter), presence of output schema, and read-only annotation, the description covers purpose, usage, and return details comprehensively. 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?

Only one parameter (todo_id) with schema description 'Productive todo ID'. The description adds no extra semantics beyond the schema. With 100% schema description coverage, 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 'Get a specific todo checklist item by ID' with a specific verb and resource. It distinguishes from sibling tools like list_todos and get_task by specifying it's for a single todo checklist item.

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 on when to use ('when you need full details of a specific todo') and lists what is returned. It implicitly excludes using for listing, but does not name alternatives like 'use list_todos instead'.

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?

Discloses that only metadata is returned (no file content) and mentions optional filtering and pagination. Annotations already indicate readOnlyHint=true, so no contradiction. Adds useful behavioral context 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?

Concise and well-structured. First line states core purpose, followed by usage hint and return details. No redundant sentences.

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 essential aspects: what the tool does, when to use it, what it returns, and that pagination is available. Output schema exists, so return details are complete. Could mention how extra_filters work, but schema description partly addresses that.

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

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

Input schema covers all 3 parameters with descriptions (100% coverage). The description does not add significant meaning beyond mentioning 'optional filtering', which is already implied by the parameters. Baseline of 3 is appropriate.

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

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

Clearly states the tool lists attachment metadata with optional filtering. The verb 'list' and resource 'attachments' are precise. Distinguishes itself from sibling tools like list_tasks, list_people, etc., which operate on different resources.

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 scenario ('when you need to browse or search attachments') and clarifies that it returns metadata only, not file content. Does not list alternative tools but the 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?

The readOnlyHint annotation already indicates it's a read-only operation. The description adds context about the returned fields (text, author, timestamps, attachments, mentions) and clarifies filtering options, including extra_filters for discussion threads. It does not contradict the annotation and provides useful behavioral details without needing to mention 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 structured with a clear purpose statement, a 'Use this when' section, a 'Returns' list, and a specific tip about extra_filters. It is somewhat wordy but each section earns its place. It is front-loaded with the core action, making it easy to scan.

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 is complete for a list tool, covering what it returns (comment metadata, parent entity, threads, attachments, mentions) and how to filter. Since there is no output schema, the description appropriately explains the return content. It includes a specific example of using extra_filters for discussion threads, which is sufficient for practical use.

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

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

The schema description coverage is 100% (all five parameters have descriptions). The description adds slight value by mentioning 'filter by project or task' and specifically calling out 'extra_filters with filter[discussion_id][eq]', but these are already implied in the schema descriptions. Since coverage is high, 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 function: 'List comments with optional filtering by project or task.' It uses a specific verb ('list') and resource ('comments'), and distinguishes from sibling tools that list other entities like tasks or attachments. The purpose is explicit and unambiguous.

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

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

The description provides a 'Use this when' clause: 'You need full comment metadata... and want to filter by specific project, task, or discussion thread.' This gives clear context for when to use the tool. However, it does not mention alternatives or when not to use it, so it lacks explicit 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 context beyond the readOnlyHint annotation by detailing the exact data returned (ID, name, archived status, etc.) and mentioning the endpoint, but does not contradict the annotation.

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

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

The description is concise with about five lines, front-loads the main action, and includes only necessary details without redundancy.

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

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

For a simple list tool with an output schema, the description covers purpose, return fields, and the endpoint, making it complete for effective usage.

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

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

Schema coverage is 100%, so the input schema already describes all parameters. The description does not add additional parameter semantics, meeting the 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 'List folders in a project' with a specific verb and resource, and lists the returned fields, differentiating it from sibling tools that handle other resources like tasks or people.

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 listing folders but provides no explicit guidance on when to use this tool versus alternatives, nor does it mention when not to use it or any prerequisites.

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

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

The description goes beyond the readOnlyHint by specifying what is returned (titles, content, metadata, project relationships) and gives practical examples. It does not mention potential side effects, but since it's read-only, that is not an issue. The return format is disclosed, adding 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 well-structured: a one-line summary, usage guidance, context, and examples. Each sentence serves a purpose without fluff. The examples are compact and illustrate key filter combinations. It is concise yet comprehensive.

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

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

Given the tool's moderate complexity (5 parameters, one nested object) and the presence of an output schema, the description covers the essential context: what it does, when to use it, return types, and usage examples. It does not explain error scenarios or limits, but those are not typically required. The description is complete enough for effective tool selection.

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

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

The input schema already covers all parameters with descriptions (100% coverage), so the baseline is 3. The tool description enhances this with concrete usage examples for extra_filters (parent_page_id and root_page_id), which clarifies how to combine parameters effectively, providing added value beyond the schema.

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

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

The description clearly states the tool lists pages/documents with filters, and distinguishes it from siblings like get_page (for single page) and quick_search (presumably broader search). It also explicitly mentions discovering subpages/subfolders, which is a distinct capability.

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

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

It provides explicit 'Use this when' guidance, including browsing by project/creator and retrieving metadata without full content. It also mentions using it for subpage discovery. However, it does not name alternative tools (e.g., quick_search) for contrast, which would make it stronger.

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 context beyond the readOnlyHint annotation by detailing specific return fields (ID, name, email, role, dates, etc.) and pagination behavior, with 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?

Efficient and front-loaded: a single sentence followed by a bulleted list of return fields, every part 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?

Fairly complete for a simple list tool with optional pagination and output schema; minor omissions like sorting or ordering but acceptable.

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

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

Schema coverage is 100% with parameter descriptions, and the description merely hints at optional pagination without adding new 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 clearly identifies the tool as listing team members with optional pagination, distinguishing it from siblings like get_person and other list_* 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?

No explicit guidance on when to use this tool vs alternatives, nor any conditions or exclusions mentioned. Usage is implied but not clarified.

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 the description adds useful behavioral context by enumerating the returned fields (ID, name, timestamps, archived status, webapp URL). It does not discuss pagination or sorting, but for a zero-parameter read-only list tool with an output schema, this 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 concise and front-loaded with the core purpose, followed by a compact bullet list of return fields. Every line adds value, and there is no redundant or vague wording.

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

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

Given the tool's simplicity (no parameters, read-only, output schema provided), the description covers what the caller needs to know about the result. It lacks explicit notes about potential result size or pagination, but this is a minor gap for a simple list operation.

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

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

The tool has no parameters, and the schema coverage is 100% by definition. The description appropriately focuses on the output, which is more relevant here, so no additional parameter guidance is needed.

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

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

The description uses a specific verb ('List') and resource ('projects') and clearly distinguishes this from sibling tools like list_tasks or list_folders. It also specifies the scope ('all projects') and the nature of the returned data.

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

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

The description implies the use case: to get a basic overview of all projects. It does not explicitly mention when to prefer this over alternatives like quick_search or list_recent_activity, nor does it provide exclusions, so guidance is only 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?

The annotations declare readOnlyHint=true, and the description adds behavioral context beyond that: it says the feed is 'summarized' and returned in 'chronological order.' It also lists what types of activities are included. These details help set expectations without conflicting with the annotation.

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

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

The description is front-loaded with a clear summary and then provides a list of examples. While the example list is lengthy (7 lines), each example is concise and directly shows parameter usage. The structure is efficient and avoids unnecessary verbosity, though it could be trimmed slightly without losing 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 has 8 optional parameters and an output schema (not shown), the description does not need to detail return values. It explains the scope of activities, the time window, and provides extensive examples covering various filters. It is sufficiently complete for an agent to understand how to invoke it appropriately.

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 each parameter is individually described. The description adds value by illustrating parameter combinations through examples (e.g., hours=168, project_id=343136). This demonstrates how parameters interact and clarifies practical usage beyond the raw 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's function: 'Get a summarized feed of recent activities and updates.' It also enumerates the types of content included (task updates, comments, new documents). While it doesn't explicitly contrast with sibling tools like get_task_history or list_comments, the emphasis on 'feed' and 'activities' makes its broad scope evident.

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 numerous usage examples via code snippets (e.g., filtering by hours, project_id, user_id, activity_type). However, it lacks explicit guidance on when to choose this tool over alternatives. The only implicit hint is in the schema for event_type, which suggests using get_tasks for closed tasks, but that's not in the description itself.

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, so no contradiction. The description adds details on pagination behavior, default sort order, and extra filter syntax, which goes 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?

The description is concise with a clear structure: one-sentence summary, bullet details, examples, and return type. Every sentence adds information, 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 complexity (6 params, nested objects) and presence of an output schema, the description covers filtering, pagination, and provides useful examples. It doesn't explain error handling or empty results, but these are minor omissions.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the opt-in nature of parameters and providing concrete examples for extra_filters, enhancing 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 tool lists tasks with optional filtering and pagination, using a specific verb and resource. It distinguishes from sibling tools like get_task and list_todos by its focus on listing multiple tasks with filters.

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

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

The description provides clear context with 'All parameters are optional - omit to fetch all tasks' and examples. However, it does not explicitly contrast with alternatives like get_task for single-task retrieval, though the purpose implies 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 indicate readOnlyHint=true. The description adds that the tool returns 'logged work records and related references', providing context beyond the annotation without contradicting it.

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 front-load the purpose. Every word adds value, with no redundancy or unnecessary detail.

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

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

The tool has an output schema, so return values are covered. The description mentions 'related references' which hints at the output structure. However, pagination behavior is not described (though parameters indicate it).

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

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

Schema coverage is 100% with detailed descriptions for all 9 parameters. The description adds a high-level summary of filters but 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 the tool lists time entries with optional date and relationship filters, specifying the verb 'list' and resource 'time entries'. It distinguishes itself from sibling tools which focus on other entities (e.g., tasks, people, folders).

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

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

No explicit guidance on when to use this tool or its alternatives. Since there are no sibling tools for time entries, usage is implied but not explicitly stated.

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

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

Annotations declare readOnlyHint=true, and the description complements this by detailing the return fields (checkbox text, completion status, assignee, etc.), adding behavioral context beyond the annotation. No destructive actions are implied, and the description does not contradict annotations.

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

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

The description is concise, front-loaded with purpose, and includes a returns section and usage guidance without any redundant or verbose content. Every sentence contributes to 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 the presence of an output schema (context signals indicate its existence), the description covers the key aspects: purpose, usage, return fields, and filtering. However, it does not mention pagination defaults or the absence of required parameters, though these are covered by the schema. Overall, it is sufficiently complete.

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

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

Schema coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the schema except for mentioning 'filter by task_id,' which is already in the schema. The extra_filters parameter is described in the schema with examples, so the description adds minimal value.

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

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

The description clearly states 'List todo checklist items with optional filtering by task,' using a specific verb and resource. It distinguishes from the sibling tool get_todo, which provides full details of a specific todo.

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 provides usage guidance: 'Use this when: You need to browse or filter checklist items across tasks... Use get_todo when you need full details of a specific todo.' This directly tells the agent when to use this tool versus an alternative.

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. The description adds that it 'lists' statuses, consistent with read-only behavior. No contradictory or additional behavioral details are provided beyond the schema.

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

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

Description is extremely concise: two sentences that get straight to the point with no unnecessary words.

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

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

Given the tool's simplicity, existence of output schema, and annotations, the description adequately covers the context. It explains what the tool returns and its purpose, though more detail about default behavior could be added.

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

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

Input schema has 100% coverage with parameter descriptions. The tool description does not add any extra meaning or context 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?

Clearly states the tool lists workflow statuses from Productive, and highlights its utility for understanding valid task status values by workflow. Distinguishes itself from sibling tools which list other entities.

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 this tool is used for understanding valid task statuses, which provides context on when to use it. However, it does not explicitly state when not to use it or name alternatives, though sibling tools are distinct.

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 include readOnlyHint=true, so the safe-read aspect is covered. The description goes beyond by explaining the 'deep_search' parameter semantics and its default behavior, which adds behavioral context. It does not contradict annotations, and the description adds value by clarifying the search breadth and depth options.

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

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

The description is well-structured with a clear summary, return-section, and examples. Each sentence earns its place by defining purpose, explaining output, and providing practical usage. It is appropriately sized for the tool's complexity and front-loads 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?

The tool has an output schema and extensive annotations, so the description need not detail return values. Given the complexity (5 parameters, 1 required), the description covers purpose, usage examples, and behavior. The schema + annotations provide technical details, and the description adds qualitative guidance, making it 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 already has 100% coverage, so description baseline is 3. The description adds some value by showing examples of usage, but it does not provide additional details on parameters like page or per_page beyond what schema lists. The search_types parameter is explained briefly in schema, and description reinforces it via examples. Overall, schema covers semantics adequately.

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 'Quick search across projects, tasks, pages, and actions' with a specific verb and resource, and differentiates from siblings like list_projects and get_task by focusing on cross-type search. It also provides examples that reinforce its scope, making it distinct and unambiguous.

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

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

The description explains it is optimized for quick lookups and general search queries, implying use cases. It gives examples with search_types to show filtering but does not explicitly state when NOT to use it or mention alternatives like list_tasks for specific searches. However, the examples provide clear context and scenario guidance.

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