Server Quality Checklist

Tool Scores

• mdr_waitA
  4.5/5.0
  Behavior5/5

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

  The description thoroughly discloses the blocking nature, timeout (90s), return values on timeout ({status:"pending"}) and completion ({status:"done"}), and the expected follow-up action ('read the file(s) to see the user's replies...'). No annotations are provided, so the description carries the full burden and handles it excellently.

  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 three sentences long, with the first sentence immediately stating the purpose, the second giving usage context, and the third covering timeout and post-completion actions. Every sentence adds value; there is no redundancy or unnecessary detail.

  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?

  For a simple wait tool with one parameter and no output schema, the description fully explains the behavior, return values, retry logic, and what to do after completion. It covers all necessary context for an agent to use the tool correctly.

  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 schema coverage for sessionId is 100%, and the description repeats the schema description ('Session ID returned by mdr_review'). It adds no extra meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'Block until the user has finished engaging with an mdr_review session.' It uses a specific verb (block/wait) and resource (mdr_review session), and distinguishes itself from sibling tools like mdr_review (which posts feedback) and mdr_ask (which likely asks questions).

  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?

  It explicitly states when to call the tool: 'Call this once after you have posted all your feedback batches via mdr_review.' It also provides guidance on timeout behavior and retry: 'If the wait times out (90s), returns {status:"pending"} — call mdr_wait again...' However, it does not explicitly mention when not to use it or alternatives, though the context is clear.

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

• mdr_askA
  4.6/5.0
  Behavior5/5

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

  No annotations are provided, so the description fully discloses behavior: returns reply text when user answers, partial replies on review finish, empty if session ends otherwise. It also explains disk persistence and pending limitation.

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

  Conciseness4/5

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

  The description is detailed but slightly long at 6 sentences. It front-loads the main purpose but could tighten some phrasing.

  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?

  Given the interactive nature and no output schema, the description fully covers return behavior, pending constraints, and integration with siblings for a complete picture.

  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?

  Schema coverage is 50%, but the description adds context by explaining the purpose of questions and anchors. However, contextAfter/contextBefore parameters lack full explanation in both schema and description.

  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 asks the user questions anchored to specific text in a file within an active review session. It distinguishes itself from siblings by mentioning inline markers and referencing mdr_review for replies.

  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 explicitly says when to use ('when a comment is unclear, or when you hit a planning fork') and provides guidance on pending constraints ('post a reply via mdr_review then retry'). It does not explicitly state when not to use, but the context is clear.

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

• mdr_request_reviewA
  4.8/5.0
  Behavior5/5

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

  The description comprehensively explains the workflow states (waiting, batch/done) and the critical constraint that during review the agent cannot read/edit files. No annotations exist, so the description carries the full burden and does so excellently.

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

  Conciseness4/5

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

  The description is fairly long but well-structured, front-loading the purpose and then providing detailed usage instructions. Every sentence appears necessary for clarity, though could be slightly more concise.

  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?

  For a tool with complex workflow (polling, state constraints), the description is remarkably complete. It covers the workflow, permission constraints, and expected result types (batch, done, not finished). No output schema, but the description explains result interpretation.

  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?

  Schema coverage is 100%, baseline is 3. The description adds value by tying filePaths to new sessions and sessionId to continuation, and reinforces the relationship with enableResolve. It provides context beyond the parameter descriptions.

  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 that the tool opens markdown files for human review or continues an existing session. It specifies the resource (markdown files) and action (request review), with clear differentiation between new and continuation sessions.

  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?

  Explicit guidance on when to pass filePaths vs sessionId, and what to do if the user hasn't finished (call again with same sessionId). Warns about not acting on files during review, which is crucial for correct usage.

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

• mdr_reviewA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: it returns immediately (non-blocking), requires passing sessionId to mdr_wait, and explains consequences of skipping mdr_wait. It also details anchoring behavior for text and fallback for diagrams, covering key traits 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.

  Conciseness4/5

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

  The description is well-structured with clear sections and front-loaded key info. It is slightly verbose but every sentence adds value, explaining the flow, anchoring behavior, and author requirement. Could be trimmed slightly, but overall efficient.

  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?

  Given no output schema and 4 parameters, the description is comprehensive: explains the two-tool flow, return sessionId, anchoring details, and agent identification. It covers all critical aspects an agent needs to use the tool correctly.

  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?

  Schema coverage is low (25%), but the description adds significant meaning: explains filePaths, the distinction between comments and replies, importance of author field, and the reason for contextBefore/contextAfter. However, it doesn't detail all parameters (e.g., enableResolve), so not fully compensating.

  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 'Review markdown files in md-redline (mdr) and leave inline feedback', specifying the verb (review), resource (markdown files), and action (inline feedback). It distinguishes from siblings by detailing the two-tool flow with mdr_wait, making its role unique.

  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?

  The description explicitly says 'Use this when the user asks you to review a doc and drop comments' and warns against skipping mdr_wait ('Skipping mdr_wait leaves a banner...'). It provides clear context for when and how to use this tool vs. alternatives.

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