Server Quality Checklist

Tool Scores

• mmap_updateA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full disclosure burden. It reveals that the map is a 'ledger' that 'never blocks you,' and explains status meanings, but does not address side effects like overwriting existing data, permission requirements, or error handling. This is moderate transparency but leaves gaps.

  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 succinct, front-loaded with the core purpose ('Update node status/label/evidence'), and every sentence adds value. It avoids fluff and is appropriately sized for the tool's complexity.

  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?

  Given the rich input schema with per-property descriptions and no output schema, the description covers the primary workflow (status transitions and evidence) effectively. It does not explain all possible updates (e.g., lanes/groups), but the schema fills those gaps, so the tool description is complete enough for the core use case.

  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 50%, and the description adds semantic meaning for status and evidence values (e.g., 'done with evidence' vs 'regressed with evidence'). However, it does not elaborate on parameters like lane, group, submap, or label beyond what the schema already says, so it doesn't fully compensate for the coverage gap.

  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 explicitly states 'Update node status/label/evidence' and provides specific examples of setting statuses (in-progress, done, regressed), making the purpose clear. It distinguishes from siblings by focusing on updating existing nodes rather than declaring, removing, or viewing them.

  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 gives clear when-to-use guidance for statuses: 'Set in-progress when starting a node... done with evidence when its verification passes, regressed with evidence when a done node breaks.' It also explains the ledger metaphor, but does not explicitly mention alternatives or exclusions relative to sibling tools.

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

• mmap_declareA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses critical behaviors: 'Edges must point strictly downward' and 'the batch is all-or-nothing.' It also hints at group rendering in the zoomed-out view. Missing details about idempotency or page behavior, but core constraints are covered.

  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?

  Three sentences: the first enumerates actions, the second gives workflow guidance, and the third states constraints. This is tight, front-loaded, and free of fluff.

  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 8 parameters and no annotations, the description provides a solid overview of the core structure. However, it omits optional parameters like page, status, submap, and detail, though the rich schema descriptions cover those. The all-or-nothing caveat adds valuable operational context.

  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 description maps high-level parameters (title, kind, layers, lanes, groups, nodes, edges) but does not detail individual parameter semantics beyond what the schema already provides. With schema coverage at 50%, it partially compensates by grouping concepts, but leaves out optional fields like page, status, submap, and detail.

  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: 'Grow the Mellos map' with specific actions (set title/kind, add layers, lanes, groups, nodes, edges). This differentiates it from siblings mmap_update/remove/view by focusing on declaring the entire structure.

  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 gives clear context: 'Declare the whole ghost design up front, then grow it as understanding deepens.' This implies initial creation and iterative growth, but it does not explicitly contrast with mmap_update, leaving some ambiguity about when to use one over the other.

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

• mmap_viewA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the transparency burden. It discloses the output format ('monochrome text'), the source/freshness ('the same picture the split-pane watcher shows live'), and the read-only intent ('check the map state', 'show it inline'). It does not detail error behavior or side effects, but the render/show framing makes the non-destructive nature clear.

  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 with no filler. The first sentence states the core function and output format; the second provides practical use cases. Every phrase adds value and the key information is front-loaded.

  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 read-only tool with two optional parameters fully described in the schema, this description is sufficient. It tells the user what the output looks like, how fresh the content is, and when to invoke the tool, so no important context is missing.

  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%, so the input schema fully documents both page and zoom, including their semantics and defaults. The description does not add parameter-level detail, which is acceptable given the schema's completeness; baseline 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 clearly states a specific verb+resource: 'Render the current Mellos map as monochrome text.' It also distinguishes this view/read tool from its mutating siblings (mmap_declare, mmap_update, mmap_remove) by emphasizing that it shows the live map rather than modifying it.

  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 gives explicit usage guidance: 'Use it to check the map state or to show it inline in conversation.' This clearly states when to use the tool, and the sibling names imply the alternatives, though it does not explicitly enumerate when not to use it.

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

• mmap_removeA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and succeeds: it discloses all-or-nothing execution, fixed removal order, cascade deletion of incident edges when a node is removed, and non-destructive ungrouping for groups. This goes well beyond the generic verb and helps the agent anticipate 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.

  Conciseness5/5

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

  Three short sentences front-load the core operation, embed side-effect rules, and close with a contextual motivation. No filler or redundancy.

  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 annotations, no output schema, and six parameters, the description covers the critical operational rules: ordering, atomicity, cascades, group ungrouping, and empty-layer constraint. It is complete enough for an agent to safely invoke the tool, with remaining parameter detail supplied by the schema.

  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 description adds meaning to node and group parameters by explaining cascading and ungrouping behavior, and refers to empty layer bands. It doesn't elaborate on edges' from/to relation or lane semantics, but the schema already documents those; overall it complements rather than repeats.

  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 opens with a specific verb and resource list: 'Remove edges, nodes, groups and empty layer bands,' with ordering and atomicity. This clearly distinguishes removal from the sibling declare/update/view tools by naming its mutating scope.

  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 gives an explicit when-to-use signal ('Use when the ghost design turns out wrong') and frames revision as intentional. It does not name alternatives like mmap_update or state when not to use, so it misses the highest bar but provides clear context.

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