Server Quality Checklist

Tool Scores

• get_documentA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, so the description does not need to restate safety. It adds that the tool returns 'full contents,' which is useful behavioral detail, but it does not elaborate on potential limitations (e.g., large documents, exact response structure), meaning it provides only marginal transparency 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.

  Conciseness5/5

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

  The description is a single, short sentence that front-loads the most important information: it returns full contents of one document. Every word earns its place, with no filler or redundant detail.

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

  Completeness4/5

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

  For a simple one-parameter tool with a read-only annotation, the description is sufficient: it states what is returned (full contents) and the document scope (one document). The lack of an output schema is mitigated by the phrase 'full contents.' It does not discuss errors or prerequisites, but those are not critical given the tool's simplicity and the schema's clarity.

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

  Parameters3/5

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

  Schema coverage is 100%, and the parameter 'slug' is already described as 'Document slug from list_documents,' which fully explains its meaning. The description contributes no additional parameter semantics, 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.

  Purpose5/5

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

  The description clearly states the tool retrieves the full contents of one document, using a specific verb ('get' implied, 'Read' in title) and resource ('document'). It distinguishes itself from sibling list_documents by explicitly focusing on a single document, which makes its purpose unambiguous.

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

  Usage Guidelines4/5

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

  The description conveys that this tool is for retrieving a single document's full contents, which implies it is the appropriate choice when a specific document is needed rather than a list. It does not explicitly mention alternatives or exclusions, but the clear singular scope provides sufficient context for typical use.

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

• list_tasksA
  4/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds value by specifying the statuses included and the extra detail that blocked tasks carry a reason, which is not in annotations or schema.

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

  Conciseness5/5

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

  The description is a single clear sentence with an em-dash, immediately conveying the tool's scope. The second clause about blocked reasons is useful and not redundant. No wasted words.

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

  Completeness4/5

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

  For a simple list tool with read-only annotations and no output schema, the description covers the essentials: what is returned, key statuses, and the blocked-reason feature. Slight gap is omitting 'failed' from the status list and not mentioning the optional limit/status filters, but overall adequate.

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

  Parameters3/5

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

  Schema coverage is 100%: both limit and status have descriptions. The tool description mentions some statuses (queued, running, blocked, done) but omits 'failed' from the enum, and does not add any additional parameter context 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.

  Purpose4/5

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

  The description states the tool lists tasks in the current plan by status ('queued, running, blocked, or done'), which is specific and distinct from sibling tools like list_documents. It lacks an explicit differentiating statement, but the resource and scope are clear.

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

  Usage Guidelines4/5

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

  The description implies usage for checking plan progress and specifically calls out that blocked tasks include reasons 'so you know what to unblock', providing a clear use context. It does not mention alternatives or exclusions, but the context is sufficient for a simple read-only list tool.

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

• create_taskA
  4.2/5.0
  Behavior4/5

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

  Beyond the annotations, the description reveals a key behavioral trait: creating a task here does not execute it; Leapd does. This adds valuable context about side effects and the division of labor, especially with openWorldHint=true.

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

  Conciseness5/5

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

  The description is two short sentences, front-loaded with the core purpose, and every word earns its place. No unnecessary detail or repetition.

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

  Completeness4/5

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

  For a simple 2-parameter create tool with good annotations and sibling context, the description is sufficient. It explains the tool's scope (creation only) and the execution handoff, though it doesn't mention return values or what happens after creation.

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

  Parameters3/5

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

  The input schema provides complete descriptions for both parameters (title and details), so the description adds no extra meaning. Baseline 3 is appropriate since schema coverage is 100% and parameters are straightforward.

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

  Purpose5/5

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

  The description uses a specific verb+resource: 'Add work to the plan' and gives concrete examples (a page to build, research, a fix). It clearly distinguishes itself from siblings like run_task by stating the task is executed by Leapd, not this MCP server.

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

  Usage Guidelines4/5

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

  The description provides clear context: use this tool when you want to add work to the plan. It implicitly differentiates from run_task by noting that execution happens elsewhere, but it does not explicitly name alternatives or state 'use run_task for execution'.

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

• get_workspaceA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, so the tool's safety profile is clear. The description adds value by enumerating the specific data fields returned (live URL, deployment/domain status, plan day, in-flight summary), which is useful 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.

  Conciseness5/5

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

  The description is a single, concise sentence that is front-loaded with 'Current state of your business' and effectively enumerates the key content. Every word earns its place, with no unnecessary filler.

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

  Completeness4/5

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

  For a tool with no parameters and no output schema, the description covers the main categories of returned information well. It could potentially add more detail about what terms like 'plan day' or 'in flight' mean, but overall it is sufficiently complete for a simple status getter.

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

  Parameters4/5

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

  The tool has zero parameters, so the description adds no parameter semantics. According to the rubric, 0 params warrants a baseline of 4; the description correctly does not attempt to describe nonexistent parameters.

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

  Purpose5/5

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

  The description clearly specifies what the tool returns: current workspace status including live URL, deployment/domain status, plan day, and in-flight summary. This distinguishes it from sibling tools focused on tasks or documents, even though the description is a noun phrase rather than an explicit verb.

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

  Usage Guidelines3/5

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

  The description implies using this tool to check workspace status, but it does not explicitly state when to use it versus alternatives or provide exclusion criteria. With zero parameters and a unique purpose, usage is fairly obvious, but no explicit guidance is given.

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

• run_taskA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate readOnly=false and destructive=false. The description adds critical behavioral nuance: it returns as soon as the task is dispatched, not when the task completes, and outcome observation requires polling list_tasks. This goes beyond annotation defaults, though it does not cover failure conditions for non-queued tasks.

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

  Conciseness5/5

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

  The description is two sentences, front-loaded with the action and followed by key return behavior. Every word contributes; no filler or redundancy.

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

  Completeness4/5

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

  For a simple action tool with one parameter and no output schema, the description covers the core behavior (dispatch), return timing, and follow-up method. It lacks explicit error handling or prerequisites beyond 'queued', but this is acceptable for a tool of this complexity.

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

  Parameters3/5

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

  Schema description coverage is 100%, with task_id fully documented as coming from list_tasks or create_task. The description does not add further semantic detail about the parameter (e.g., format or validation), so the baseline of 3 applies.

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

  Purpose5/5

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

  The description uses a specific verb ('Start') and resource ('a queued task') and clearly distinguishes the action from waiting for a scheduled slot. It also differentiates from sibling tools like create_task (creating) and list_tasks (listing), 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.

  Usage Guidelines4/5

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

  The description states when to use the tool ('instead of waiting for its scheduled slot') and directs users to poll list_tasks for outcomes, providing follow-up guidance. It does not explicitly name alternative tools, but the implicit contrast is sufficient for most use cases.

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

• launch_businessA
  4.4/5.0
  Behavior4/5

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

  The description discloses that the tool creates a live business (positioning, landing page, plan) and returns a public URL. It warns against multiple invocations. This goes beyond the basic safety annotations (readOnly=false, openWorld=true) by detailing the specific artifacts produced.

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

  Conciseness5/5

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

  Two sentences, front-loaded with the core action, then usage guidance. No redundancy.

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

  Completeness4/5

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

  The description covers the main purpose, key output (public URL), and next step (get_workspace). It lacks details on edge cases or side effects, but given the sibling tools and schema richness, it is sufficient.

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

  Parameters3/5

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

  Schema covers all three parameters with descriptions, so the baseline is 3. The tool description does not elaborate on parameter usage beyond the schema, though it reinforces that 'idea' is the core input.

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

  Purpose5/5

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

  The description states a specific action ('Turn an idea into a live business on Leapd') with clear deliverables (positioning, deployed landing page, day-one plan) and return value. It distinguishes itself from siblings by noting it launches a business and pointing to get_workspace for subsequent use.

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

  Usage Guidelines5/5

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

  Explicitly instructs 'Call this once — use get_workspace afterwards,' giving clear when-to-use and a next-step alternative. This distinguishes it from read-only tools like get_workspace/list_tasks.

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

• list_documentsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the description doesn't need to restate safety. It adds value by specifying the return format ('slugs and titles') and the document scope, going beyond the annotations. There is no contradiction, and the lack of pagination/filtering details is acceptable for such a simple list tool.

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

  Conciseness5/5

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

  Two sentences, front-loaded with the all-important scope ('Artifacts Leapd has produced'), then the return payload, then a cross-reference to get_document. Every word earns its place; no redundancy or filler.

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

  Completeness5/5

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

  With no parameters, no output schema, and clear annotations, the description is fully complete for its simplicity. It even tells the agent what the tool returns and what to use next to read a document. There is no missing information that would prevent correct invocation.

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

  Parameters4/5

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

  The tool has zero parameters, so schema coverage is 100% vacuously. The description adds no parameter details because none are needed, and the baseline for 0 parameters is 4. The mention of return fields partially compensates for lack of an output schema.

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

  Purpose5/5

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

  The description specifies a clear verb ('List') and resource ('documents'), and further defines the scope as 'Artifacts Leapd has produced' with examples. It clearly distinguishes from siblings like get_document (which reads one) and list_tasks (which lists tasks, not documents).

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

  Usage Guidelines4/5

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

  The description implies its use for obtaining an overview of documents and explicitly directs to 'use get_document to read one,' providing an alternative for deep reads. However, it doesn't discuss when not to use this tool versus other list tools like list_tasks, though the context signals make that distinction implicit.

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