Server Quality Checklist

Tool Scores

• impact_emitA
  4.8/5.0
  Behavior5/5

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

  Annotations already mark the tool readOnly and non-destructive. The description goes further and adds materially useful behavioral detail: the analysis is offline and plan-only, no cloud credentials are used, a plan-only manifest can never claim 'safe', and the full manifest is written to a private temp file rather than returned inline due to size. 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.

  Conciseness5/5

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

  The description is moderately long but every sentence earns its place: purpose, parameter format, safety/behavioral caveats, and return value are each covered in a clean, front-loaded structure. No filler or repetition.

  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 one parameter, safety annotations, an output schema, and a single sibling, the description covers everything needed: what it produces, what input it accepts, key limitations, the handle-based return contract, and the follow-up tool. Nothing important is missing.

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

  Parameters5/5

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

  The input schema provides no description for plan_path (0% coverage), so the description carries the full burden. It does this excellently by specifying that plan_path may point at 'terraform show -json' output or a saved .tfplan file, and that conversion is automatic. This is exactly the semantic information an agent needs.

  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: 'Produce an Impact Manifest... from a Terraform plan, using blastcheck.' It clearly states what the tool creates and from what input, and distinguishes it from the obvious sibling impact_explain by noting the returned handle is meant to be passed there.

  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 for when to use impact_emit: when you need to generate a plan-only Impact Manifest from a Terraform plan. It explicitly routes the downstream step to impact_explain via the manifest_handle. It does not spell out 'when not to use' or formal alternatives, but the relationship to impact_explain is clear enough.

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

• impact_explainA
  4.8/5.0
  Behavior5/5

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

  Beyond the readOnly/destructive annotations, the description discloses substantial behavior: a hard character budget with an env-var override, compact grouped rendering with an explicit partial-view notice ('never a silent cut'), AND-combined filters, addresses always rendered in full detail, and lexical sorting for deterministic output. These are exactly the non-obvious traits that would otherwise surprise an agent.

  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?

  Despite its length, every sentence earns its place: purpose, input modes, output format, budget behavior, filter semantics, and determinism. The most decision-relevant info (what it does, what to provide) is front-loaded, and no sentence repeats the schema or annotations.

  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 7 optional parameters, an output schema, and meaningful failure/edge behavior (budget overruns, partial views), the description is complete. An agent can correctly select an input mode, choose filters, and predict the response shape without opening the schema or chasing external docs.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description carries the full burden — and it delivers. All 7 parameters get meaningful semantics: manifest_handle's provenance, manifest_path's on-disk nature, manifest as inline document, severity with an example value, module_prefix as address prefix, resource_type with an exact-match caveat and example, and addresses as the guaranteed full-detail path. It fully compensates for the empty 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?

  Opens with a specific verb-plus-resource statement ('Explain an Impact Manifest in plain language') and then details the output contents (verdict, findings, safe-if checklist, unverifiable items), making the tool's job unmistakable. The explain/emit verb pair cleanly distinguishes it from the only sibling, impact_emit.

  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 on the three mutually exclusive input modes (manifest_handle 'from impact_emit', manifest_path on disk, manifest inline) and how the optional filters narrow the view. It stops short of an explicit when-not-to-use statement relative to impact_emit, but the pointer that manifest_handle comes 'from impact_emit' effectively orients the agent to the sibling's role.

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