Server Quality Checklist

Tool Scores

• strale_searchA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It successfully discloses cost behavior ('Free to search', 'Most under €0.10') and scope ('250+'). However, it omits pagination behavior details, rate limits, and return format structure despite the presence of an offset parameter implying paginated results.

  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 front-loaded with the core purpose and efficiently structured: scope claim → categorical proof → pricing context. Every element earns its place; the parenthetical examples justify the '250+' claim while helping users identify relevant search terms.

  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 search tool with good schema coverage, the description adequately covers the searchable domain and cost model. It falls short of describing the return value structure (which would help given no output schema exists), but provides sufficient context for an agent to understand what capabilities exist within the Strale ecosystem.

  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%, documenting query, category, and offset sufficiently. The description does not explicitly reference these parameters, but given the comprehensive schema coverage, no additional parameter semantics are required from the description text.

  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 ('Search Strale's 250+ API capabilities'), clearly positioning it as a discovery tool. The extensive category list (KYC, validation, Web3, etc.) distinguishes it from execution-focused siblings like strale_execute and strale_transaction.

  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 provides implicit usage guidance by listing searchable categories (compliance, validation, etc.), indicating when to use the tool. However, it lacks explicit contrast with siblings—particularly failing to state that users should search here before invoking strale_execute.

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

• strale_balanceA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses the return format (EUR cents and EUR) and authentication requirement. However, it does not explicitly state that this is a read-only, safe operation or contrast its non-destructive nature against mutation siblings like strale_transaction.

  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 with zero waste. The first sentence covers functionality and return format; the second covers authentication requirements. Information is front-loaded and appropriately sized for a simple zero-parameter tool.

  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 balance retrieval tool with no input parameters and no output schema, the description is nearly complete. It specifies the currency formats returned and auth needs. It could be improved by explicitly stating the read-only nature given the lack of annotations and presence of mutation siblings.

  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 input schema has zero parameters with 100% coverage (trivially). Per scoring rules, zero parameters establishes a baseline of 4. The description appropriately does not discuss parameters since none exist, focusing instead on return value semantics and auth requirements.

  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 (Returns) with the exact resource (Strale wallet balance) and specifies the dual return format (EUR cents and EUR). This clearly distinguishes it from siblings like strale_execute and strale_transaction which imply state modification, while this tool clearly retrieves data.

  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 states the prerequisite 'Requires an API key,' providing necessary auth context. However, it lacks explicit guidance on when to use this versus alternatives (e.g., 'use this to check funds before calling strale_execute') or 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.

• strale_getting_startedA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses the authentication context ('without an API key') and implies a read-only operation ('Returns'), but omits other behavioral traits like rate limiting, caching behavior, idempotency, or the specific data format/structure of the returned capabilities list.

  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 zero waste. It front-loads the value proposition (free, no API key) and efficiently lists capabilities using a parenthetical format that packs maximum information into minimal space. Every clause 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 this is a zero-parameter tool with no output schema, the description adequately covers what the agent can expect to receive (a list of free capabilities and setup steps). While it does not specify the technical return structure (JSON schema), it conceptually completes the picture sufficiently for tool selection.

  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 input schema contains zero parameters, which establishes a baseline of 4 per the scoring rules. The description correctly provides no parameter details since none exist, and does not invent fictional 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 explicitly states the tool 'Returns free capabilities you can use immediately without an API key' and lists five specific capabilities with parenthetical explanations of what each does (e.g., 'email-validate (verify email deliverability)'). It also clarifies it returns 'setup steps for full access to 250+ paid capabilities,' clearly distinguishing it from operational siblings like strale_execute or strale_transaction that likely require authentication.

  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 usage context through phrases like 'without an API key' and 'getting started' (in the tool name), suggesting it serves as an entry point for exploration before full setup. However, it lacks explicit guidance on when *not* to use this versus siblings (e.g., 'use strale_execute instead for paid capabilities') or prerequisites beyond the API key distinction.

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

• strale_methodologyA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively compensates by detailing the comprehensive nature of the returned methodology (5×5 matrix, 1340 test suites, provenance tracking, current limitations), giving the agent clear expectations about the informational scope and depth of the response.

  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 information-dense but well-structured, moving logically from high-level concept (dual-profile model) to specific components (4 factors each, 5×5 matrix) to operational details (test infrastructure, audit trails) to limitations. Every clause adds specific content details without redundancy, though the single-sentence density approaches the limit of optimal readability.

  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?

  Despite lacking an output schema, the description comprehensively enumerates the methodology components an agent can expect (scoring models, execution guidance, test infrastructure statistics, badge system, limitations). This effectively substitutes for formal output documentation by setting clear expectations about the knowledge base being retrieved.

  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 input schema defines zero parameters (empty object). According to calibration rules, 0 parameters establishes a baseline score of 4. The description correctly requires no additional parameter explanation since there are no inputs to document.

  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 ('Get') and resource ('Strale's quality and trust methodology'), then elaborates extensively on scope: dual-profile scoring model, Quality/Reliability Profiles, SQS confidence score, test infrastructure, and audit systems. It clearly distinguishes from sibling strale_trust_profile by focusing on explanatory methodology rather than specific profile data retrieval.

  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 thoroughly documents what content is returned (scoring matrices, test suites, badge systems), allowing agents to infer this is for understanding Strale's evaluation framework. However, it lacks explicit when-to-use guidance or comparison to alternatives like strale_trust_profile (e.g., 'use this to understand scoring methodology, use strale_trust_profile to retrieve specific component ratings').

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

• strale_pingA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It compensates well by explicitly listing what the tool returns (server status, counts, response time), effectively describing the output behavior despite the lack of an output 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?

  Three efficient sentences with zero waste: declarative identification ('Health check'), specific return values, and functional purpose ('Verifies the connection'). Every sentence earns its place.

  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 tool's simplicity (zero parameters) and lack of output schema, the description is complete. It documents the return values that would otherwise be unknown and adequately describes the tool's single purpose.

  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 input schema defines zero parameters, establishing a baseline score of 4. The description correctly requires no additional parameter clarification.

  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 identifies this as a 'Health check' that returns specific diagnostics (server status, tool count, capability count, response time). It clearly distinguishes this diagnostic tool from operational siblings like strale_execute and strale_transaction.

  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 phrase 'Verifies the connection is working' provides clear context for when to use this tool (connection verification/diagnostics). While it doesn't explicitly name alternatives or state 'use this first,' the health check purpose naturally contrasts with the operational sibling tools.

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

• strale_transactionA
  4.5/5.0
  Behavior4/5

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

  With no annotations, description carries full burden and discloses return payload details (inputs, outputs, latency, price, provenance, status) and authentication behavior ('Free-tier transactions are accessible by ID without an API key'). Lacks explicit safety classification or rate limit details.

  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 tightly constructed sentences: action/returns, usage guidance, and auth note. Every sentence delivers distinct value with 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?

  For a single-parameter retrieval tool, description fully compensates for missing output schema by enumerating all returned fields (latency, price, provenance, status). Covers debugging, audit, and auth contexts comprehensively.

  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 has 100% coverage with 'transaction_id' already described as 'Transaction ID returned from a strale_execute call'. Description mentions 'by transaction ID' but does not add syntax, format, or constraint details beyond the schema. Baseline 3 appropriate for high schema coverage.

  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?

  Description opens with specific verb 'Retrieve' and resource 'past execution record', clearly distinguishing this lookup tool from sibling 'strale_execute' by referencing 'previous strale_execute call'.

  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 states three use cases: 'inspect what a previous strale_execute call returned, debug failures, or provide an audit trail', directly naming the sibling tool and clarifying when to use this vs. the execution tool.

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

• strale_executeA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full disclosure burden. It successfully documents return format ('structured JSON output with SQS quality score, latency, and data provenance'), pricing model (free vs paid capabilities), and data provenance. Lacks explicit error handling or destructiveness guidance, but covers the primary behavioral traits given the generic executor nature.

  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 dense sentences with zero waste: (1) purpose + examples, (2) output format, (3) auth/pricing + sibling dependency. Front-loaded with core action, examples provide concrete anchors, and workflow instruction is clear. No redundancy with schema fields.

  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?

  Compensates well for missing output schema by detailing return structure (SQS score, latency, provenance). For a complex meta-tool executing 250+ capabilities, it adequately covers the dependency chain (strale_search → strale_execute), pricing, and return format. Could enhance with error handling or rate limit notes, but functionally complete.

  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 3). The description adds value by providing concrete slug examples ('swedish-company-data', 'vat-validate') and explaining that inputs must match 'capability's required fields' discoverable via strale_search. It also contextualizes max_price_cents by listing free capabilities.

  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-resource pair ('Run a Strale capability by slug') and provides concrete examples (IBAN validation, company lookup, sanctions screening) that clearly distinguish it from siblings. It specifically differentiates from strale_search by stating this tool executes while search discovers.

  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 states the prerequisite workflow: 'Use strale_search first to find the right slug and required inputs.' This provides clear when-to-use guidance relative to the sibling tool. Also clarifies authentication requirements (free capabilities work without API key) and implies when max_price_cents matters.

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

• strale_trust_profileA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and comprehensively discloses return values (SQS score, A-F grades, 30-day pass rate, cost envelope) and behavioral guidance (call directly, retry with backoff, queue, or fallback).

  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 information-dense sentences with zero waste. First sentence front-loads purpose and detailed return structure; second provides usage context. Appropriate length for a tool with no output schema requiring manual return documentation.

  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?

  Excellent completeness given no output schema exists. Description compensates by enumerating all return fields (scores, grades, limitations, cost) and explaining the decision-making framework, fully preparing the agent to interpret results.

  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 both 'slug' and 'type' fully documented in the input schema. The description references 'capability' implicitly mapping to the slug parameter, but primarily focuses on return values rather than adding parameter semantics.

  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 specific verb 'Check' with resource 'capability reliability' and scope 'before calling it', clearly distinguishing this introspection tool from sibling execution tools like strale_execute.

  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 states 'Use this to decide whether a capability is safe for production use right now' and implies the workflow order (check before calling) relative to strale_execute, with clear decision points for execution strategies.

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