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

Annotations indicate a non-read-only, non-destructive operation. The description explicitly states it creates a new project folder and returns the created object with generated ID and timestamps, which is consistent with annotations. It adds useful context about the shared workspace but does not discuss permissions or error behavior. Given the annotations already set expectations, this is solid.

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 opening sentence, a brief explanatory line, useful examples, and formatted Args/Returns sections. Every sentence serves a purpose; there is no fluff or redundancy.

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

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

For a simple creation tool with 3 parameters, the description is complete: it states the purpose, workspace context, parameter meanings, and return value. The sibling tools imply the broader workflow, and there is no output schema to explain. No significant 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 description coverage is 100%, so each parameter is already documented. The description repeats the parameter explanations nearly verbatim, adding only a slight elaboration on 'metadata' (e.g., framework references). It does not add significant semantic value beyond the schema, so a 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 opens with a specific verb and resource: 'Create a new project folder in the shared dialogue workspace.' It further clarifies that projects are top-level containers for conversation threads, which distinguishes it from sibling tools like dialogue_create_thread. The examples reinforce the intended scope.

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

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

The description provides clear context: projects are top-level containers for related threads, implying this tool is for creating those containers. It does not explicitly name alternatives or exclusion criteria, but the sibling tool list and phrasing make the use case evident.

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 all false, giving no safety hints. The description adds context about the initiated_by parameter and the return value, but it does not disclose potential errors, prerequisites, or side effects. It does not contradict annotations, but the behavioral disclosure is limited.

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 Args and Returns sections and front-loads the main purpose. It is slightly verbose due to redundancy with the schema, but every sentence contributes to 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?

With no output schema, the Returns section is helpful. The description explains what threads are and covers required parameters. However, it omits potential error cases or prerequisites like the project existing, leaving some gaps for a create tool.

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

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

Schema coverage is 100% and the schema provides detailed parameter descriptions, especially for initiated_by. The description's Args section mostly repeats schema information without adding significant meaning, so the baseline of 3 is appropriate.

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

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

The description explicitly states 'Start a new conversation thread within a project,' using a specific verb and resource. It clearly distinguishes this tool from siblings like dialogue_create_project and dialogue_post_message.

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

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

The description provides context about threads as named conversations between Claude.ai and Claude Code, implying when this tool is appropriate. However, it does not explicitly state alternatives or exclusions, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful return behavior: 'Complete project object or error if not found.' This goes beyond annotations by describing success and error outcomes, though it doesn't cover auth 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?

The description is compact and front-loaded with a clear purpose statement. The structured Args/Returns format makes it easy to parse. Every sentence earns its place with no redundancy or 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 tool's simplicity (single parameter, no output schema) and strong annotations covering safety, the description provides enough context. It explains the return type and error behavior, which is sufficient for an agent to select and invoke this tool correctly.

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

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

Schema coverage is 100%; the schema already documents project_id as 'The project ID'. The description repeats this but adds no extra semantics about format, constraints, or usage. Baseline 3 is appropriate when the schema carries the parameter meaning.

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

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

The description clearly states the verb and resource: 'Get full details of a specific dialogue project.' This distinguishes it from siblings like dialogue_list_projects (which lists projects) and dialogue_read_thread (which reads threads). No ambiguity.

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

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

The description implies usage when you need full details of a specific project by ID. It doesn't explicitly mention alternatives or exclusions, but the context is clear for a standard get-by-ID operation. There is no misleading guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds context beyond this by stating the scope ('shared workspace') and the return shape (array of project summaries with specific fields). This provides useful 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 concise and well-structured. It front-loads the primary function, then adds return summary and usage guidance, followed by a clear Args section and Returns description. Every sentence earns its place, and there is 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?

For a simple list operation with good annotations and one optional parameter, the description is complete. It explains the tool's purpose, the return format (array of summaries), and the usage context. No output schema exists, so the description adequately covers return values. No critical gaps are apparent.

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

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

There is one parameter with 100% schema coverage. The description repeats the parameter's name, options, and default exactly as in the schema, adding no extra semantic value (e.g., usage examples, format implications). Baseline 3 is appropriate because the schema carries the parameter documentation.

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 begins with a specific verb and resource: 'List all dialogue projects in the shared workspace.' It clearly distinguishes from sibling tools like dialogue_get_project (single project) and dialogue_list_threads (threads) by focusing on listing projects, and it notes the return summary. The purpose is unambiguous and well-scoped.

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: 'Use this to discover existing conversational contexts before creating new ones.' This tells the agent when to invoke this tool. However, it does not explicitly mention alternatives or when not to use it (e.g., use dialogue_get_project for a specific project ID), so it stops short of a 5.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, indicating a safe read operation. The description adds valuable behavioral context beyond the annotations: it specifies the exact fields in the summaries, sorting by most recently updated, default limit, and pagination. This provides strong transparency without contradicting the structured signals.

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

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

The description is concise and well-structured: it leads with the main purpose, followed by return details, an Args list, and a Returns note. Every sentence contributes useful information, and the formatting makes it easy to scan. No redundant or vague 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?

Despite having no output schema, the description fully explains return values (thread summaries with specific fields, pagination), sorting behavior, and parameter defaults. It covers all key aspects needed for an agent to select and invoke the tool correctly, and it is consistent with the annotations and 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?

The input schema has 100% description coverage for all four parameters, so the description's Args section largely duplicates the schema. It adds no new semantic meaning. There is a minor inconsistency ('offset' described as 'number' but schema says 'integer'), but this does not enhance understanding, 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 'List conversation threads within a project' with a specific verb and resource, and distinguishes from siblings like dialogue_read_thread by focusing on listing multiple threads with summaries rather than reading a single thread. This makes the tool's purpose unambiguous and well-differentiated.

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

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

The description provides clear context for when to use this tool (listing threads within a project, optional status filter, pagination) but does not explicitly mention alternatives or exclusions, such as when to use dialogue_search instead. It falls short of a 5 because it lacks direct comparison or when-not-to-use guidance.

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

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

Annotations indicate a write operation (readOnlyHint=false) but no destructive or idempotent hints. The description adds valuable behavior context: messages are 'appended to the thread's history and are immediately visible to the other instance,' clarifying the non-destructive, atomic-like nature. It also states the return value (created message object with ID and timestamp), though it does not address failure modes or prerequisites.

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 appropriately sized with a clear structure: a one-sentence summary, a short contextual paragraph, a bulleted Args list, and a Returns note. Every element adds value, although the Args list partially duplicates the schema descriptions; the added semantics justify the length. It is 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 has 5 parameters, no output schema, and is the core communication primitive, the description is complete. It explains the purpose, role semantics, message behavior (append/visibility), and return value. It also covers optional metadata and the required parameters. No critical information 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?

Schema coverage is 100%, so baseline is 3. The description adds extra meaning by explaining that role identifies which instance speaks, content is flexible ('prose, code, structured notes'), and metadata is a JSON string for structured data. This goes beyond the basic property descriptions in the schema, providing context for each parameter's intended use.

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: 'Post a message to a dialogue thread as either claude_app or claude_code.' It uses a specific verb and resource, and distinguishes itself from siblings by positioning itself as 'the core communication primitive' among read/manage/search tools.

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

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

The description provides clear context on when to use the tool: it is the core communication primitive, implying it is the primary way to send messages in the dialogue system. It also explains how the role parameter determines which instance posts. However, it does not explicitly mention when not to use it or list alternative tools for specific situations.

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

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds useful context: returns metadata plus messages in chronological order and supports pagination, which annotations don't convey.

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 short sections, front-loaded summary, and no fluff. The Args block is redundant with schema but still concise and readable.

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 adequately explains the return payload (metadata + messages in order) and pagination behavior. All parameters are described, and the presence of annotations covers safety expectations.

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's Args section mostly duplicates schema descriptions without adding new meaning. It provides defaults for offset/limit, but these are also in the schema.

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

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

The description clearly states the tool reads the full conversation history of a thread, using specific language ('read', 'thread') that distinguishes it from siblings like dialogue_search or dialogue_list_threads.

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 reading thread history and explicitly recommends offset/limit for long threads. It doesn't name alternatives or exclusion conditions, but the purpose is clear enough to guide 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?

Annotations already indicate safe read-only behavior, so the description adds value by disclosing that it searches across titles, tags, and message content, and returns thread summaries rather than full messages. This gives useful context beyond the annotations, though it does not cover edge cases like pagination or case sensitivity.

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 appropriately concise, front-loaded with the core purpose, and followed by a clean Args/Returns block. Every sentence adds value without redundancy, 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?

For a simple search tool with 2 parameters and no output schema, the description explains the search scope, the parameters, and the return type (array of thread summaries). It is complete enough for most use cases, though it omits details like summary structure or error behavior.

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

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

Schema description coverage is 100%, meaning the schema already fully documents both parameters. The description repeats the parameter meanings without adding extra detail, such as formatting, constraints, or interplay between parameters, so it stays at 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 it searches across thread titles, tags, and message content, which is a specific verb+resource. It distinguishes itself from siblings like dialogue_list_threads (which likely lists without searching) and dialogue_read_thread (which reads a single thread), making the purpose unambiguous.

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

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

The description specifies that it can search within a specific project or across all projects, providing clear context on when to use it. It does not explicitly mention alternatives or exclusions, but the scope and behavior are sufficiently clear for most search scenarios.

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

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

The annotations already indicate idempotency and non-destructive behavior, so the description doesn't need to repeat those. It adds the return value ('Updated thread object') and explains the semantics of each status, which are useful behavioral details beyond the annotations and not contradictory.

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 main purpose, followed by two concise usage tips, a compact args list, and a return line. Every sentence serves a purpose, with no unnecessary repetition 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 three-parameter status update tool, the description fully covers the action, valid statuses, and return type. The annotations supply idempotency and non-destructive hints, and the absence of an output schema is mitigated by the explicit return statement. No additional context is 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?

The input schema covers all three parameters with descriptions and an enum for status, achieving 100% schema coverage. The description's Args section largely restates the schema, and the additional status usage notes replicate the schema's own descriptions, so it adds little meaning beyond the structured data.

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 'Change a thread's status to active, resolved, or archived' with a specific verb and resource, and enumerates the allowed values. This distinguishes it from sibling tools like dialogue_create_thread or dialogue_post_message, which have different purposes.

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 'resolved' versus 'archived', helping the agent choose the correct status. It does not explicitly name alternatives or exclusions, but the purpose is unambiguous, and the sibling context makes it clear that this is the dedicated status-change tool.

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