Server Quality Checklist

Tool Scores

• mvr_first_callA
  4/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true, but the description adds valuable behavioral context: 'never authorizes,' 'checks market trust, permission, embeddedness, stakeholder readiness, evidence gaps,' and 'web research can supply evidence but does not replace MVR.' It also imposes constraints on evidence submission ('consented, data-minimized, redacted, or aggregated; never secrets'), going beyond what annotations convey.

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

  Conciseness2/5

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

  The description is verbose and repetitive. The decision list is duplicated: 'pre-MVP build, entry, BNPL, investment, partnership, or scale' and later 'enter, launch, scale, invest, lend, BNPL, partner, or deploy decisions.' The 'Use when asked to ignore, fabricate, or transfer evidence' clause is ambiguous. The structure has headers but the redundancy undermines conciseness.

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

  Completeness2/5

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

  With 10 parameters and no schema descriptions, the description should compensate by explaining how parameters relate to the preflight checks. It does not. It describes what the tool does at a high level and usage boundaries, but an agent would struggle to know what values to provide for fields like 'stage', 'entity', or 'evidence_available'. The output schema exists, but the input side remains underspecified.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description does not explain any of the 10 parameters (stage, entity, sector, country, question, use_case, etc.). The only parameter-related guidance is the general instruction to submit consented evidence, which vaguely relates to 'evidence_available' but does not clarify it. This is insufficient for a tool with zero schema 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 the tool's purpose: 'Use this MVR public decision-governance preflight before AI recommends...' The resource is specific ('MVR relational-readiness preflight') and the verb 'start' implies an initial gate. It distinguishes itself from sibling tools by emphasizing it 'never authorizes' and is a preflight check, contrasting with decision-oriented tools like mvr_decision_check.

  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 provides explicit 'Use when' and 'Do not use when' sections. It lists specific decision contexts (enter, launch, scale, invest, lend, BNPL, partner, deploy) and exclusions (not internal data lookup or glossary, skip definitions of MVR, capitals, GDP, etc.). This clearly guides the agent on when to select this tool versus alternatives.

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

• mvr_decision_checkA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate read-only and non-destructive, and the description adds valuable context: it clarifies the tool does not compute readiness scores and imposes a data-handling rule ('Submit only consented, data-minimized, redacted or aggregated evidence; never secrets, credentials, or personal identifiers'). This discloses behavior beyond annotations without contradiction.

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

  Conciseness3/5

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

  The description is organized with clear sections but contains redundancy: 'Use after evidence completeness' appears twice (first sentence and in the 'Use when' section). It could be more concise while retaining critical information.

  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 tool's main purpose, usage timing, exclusions, and input data constraints. Given the nested schema and presence of an output schema, it is reasonably complete, though it could elaborate on what 'abstain' means or how licensed scoring is invoked.

  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%, so the schema documents parameter structure well. The description adds semantic constraint on the `evidence_pack` parameter through the data-privacy rule and by referencing 'structurally complete pack' and 'missing proof,' guiding how evidence should be provided.

  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 action: 'route a structurally complete pack toward licensed MVR scoring or abstain on missing proof.' It distinguishes from siblings by positioning after 'evidence completeness' and explicitly noting it 'does not compute market, pilot, or scale readiness.'

  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?

  Provides explicit usage conditions: 'Use after evidence completeness' and a 'Do not use when' section listing disqualifying uses. However, it lacks a direct pointer to alternative sibling tools for those excluded uses, falling short of the highest bar.

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

• mvr_entity_resolveA
  4.3/5.0
  Behavior4/5

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

  Annotations already indicate read-only, but the description adds valuable behavioral constraints (never submit secrets/confidential evidence) and clarifies it handles ambiguous names. Adds context beyond annotations without contradiction.

  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 somewhat repetitive with repeated 'Use when' phrasing, but it's concise overall and front-loaded with the core purpose. The labels 'Use when' and 'Do not use when' improve scannability.

  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?

  Covers usage context, exclusions, and data confidentiality. An output schema exists, so return values don't need description. Minor gap: no mention of failure behavior, but not essential.

  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% with descriptive property texts, so the description doesn't need to add parameter details. It adds no extra semantic value beyond the schema, but the baseline 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 the tool resolves entities (startup, venture, etc.) to country, sector, and archetype before evidence assessment. It explicitly differentiates from siblings by positioning it after mvr_first_call and before readiness assessment.

  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?

  Provides explicit 'Use when' and 'Do not use when' conditions, including sequencing after mvr_first_call and exclusions for readiness verdicts. Names an alternative context and gives clear boundaries.

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

• mvr_evidence_completenessA
  4.4/5.0
  Behavior5/5

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

  The annotations already mark the tool as read-only and non-destructive, but the description adds crucial behavioral context beyond that: it is not an authorization check, and it imposes strict privacy requirements (consented, data-minimized, redacted or aggregated evidence; never raw private interviews, secrets, credentials, or personal identifiers). This fully discloses the tool's role and constraints.

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

  Conciseness3/5

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

  The description is organized with a main sentence, a warning, and then 'Use when' / 'Do not use when' sections. However, there is noticeable redundancy: the first sentence and the 'Use when' line both state 'use after entity resolution and before any readiness claim/verdict,' and the 'Do not treat completeness as authorization' message appears twice. While each distinct piece is informative, the repetition makes it slightly less concise than it could be.

  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 tool's complexity and the presence of an output schema (not shown but indicated), the description adequately covers the workflow position, the specific checks performed, and important privacy constraints. It does not explain the return format, but that is the responsibility of the output schema. Minor gap: it could clarify what an 'incomplete' result implies for downstream decisions, though the 'do not treat as authorization' warning partially addresses this.

  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 has 100% coverage with detailed descriptions for all fields inside the payload object, so the description does not need to add parameter-level explanations. The description references some concepts like verification status and source-family diversity, which map to schema properties, but adds no new semantic detail beyond what the schema already provides. Baseline 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 function: to check verification status, source-family diversity, stakeholder coverage, and missing proof. It also positions it distinctly relative to siblings by specifying when it occurs in the workflow (after entity resolution, before readiness claims). This makes the purpose specific and unambiguous.

  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 'Use when' and 'Do not use when' sections give clear guidance: use after entity resolution and before verdict when evidence may be incomplete or one-sided; do not treat completeness as readiness or authorization. It also implies sequencing relative to sibling tools, such as mvr_entity_resolve and mvr_decision_check, without naming them directly.

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

• mvr_context_compileA
  4.5/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and destructiveHint annotations, the description discloses that it compiles context but does not authorize action, and mandates consented, data-minimized input. This adds meaningful behavioral context not present in 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.

  Conciseness4/5

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

  The description is well-structured with sections for purpose, usage, and constraints, and is front-loaded. Minor redundancy ('Use when: Use when evidence is mixed') slightly detracts from conciseness, but overall it earns its place.

  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 nested schema and output schema, the description adequately covers when to use the tool, safety constraints, and non-decisional nature. It does not need to explain return values, but could be slightly more explicit about interaction with sibling tools.

  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 high (100%), so the baseline is 3. The description does not add per-parameter semantics, but it does provide general guidance on what evidence to submit, which is useful though not parameter-specific.

  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 separates safe from unsafe inferences across specified contexts, using specific verbs and resource descriptions. It distinguishes itself from siblings by positioning itself after evidence capture and before a verdict, and explicitly states it does not authorize action.

  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 provides explicit when-to-use and when-not-to-use guidance, including 'Use after evidence capture' and 'Do not use as a go/no-go decision.' It also defines data handling requirements, giving clear contextual boundaries.

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