Server Quality Checklist

Tool Scores

• blekline_log_governance_eventB
  3.4/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=false and destructiveHint=false, and the description adds behavior context: it is metadata-only and does not store raw prompt content. This goes beyond the annotations without contradicting them.

  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 short sentences with no redundant words. The first sentence states the action and target, the second adds a critical constraint, earning its place.

  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?

  Given five undocumented parameters and no output schema, the description is too sparse. It provides some context (metadata-only, no raw content) but fails to explain parameter purposes, return values, or when to use the tool relative to similar siblings, making it incomplete for a tool of this complexity.

  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%, so the description must explain parameter meanings, but it does not mention any of the five parameters (kind, action, platform, riskTier, entitiesMasked). The description only states the tool's general behavior, leaving parameter semantics entirely to the schema.

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

  Purpose4/5

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

  The description clearly states it writes a metadata-only governance audit event, which is a specific verb and resource. However, it does not explicitly distinguish itself from sibling tool 'blekline_emit_event' beyond the 'governance' qualifier.

  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 this is for governance audit logging with the 'governance audit event' phrasing, and the 'Does not store raw prompt content' hints at when to choose this over alternatives. No explicit exclusions or alternative tool references are given.

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

• blekline_evaluate_tool_callA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, and the description repeats this with 'Read-only' without adding new safety information. However, it does add value by disclosing that the policy outcome can be 'allow, mask, or block,' which is useful behavioral context not present in the annotations. No contradiction exists.

  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 a single, well-structured sentence that front-loads the key attribute ('Read-only') and immediately follows with the specific action and policy outcome. Every word contributes, with no redundancy or filler, making it an exemplar of conciseness.

  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 tool is simple and the description covers its core purpose and outcome categories. While there is no output schema to define return values, the mention of 'allow, mask, or block' implicitly communicates the possible results, and the safety profile is well-covered by annotations. The only gaps are the unexplained 'platform' parameter and minor details about argument handling, but overall it is sufficiently complete for an agent to use 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?

  With 0% schema description coverage, the description carries the burden of explaining parameters. It explicitly mentions 'tool name and arguments,' which maps to the required toolName and arguments properties, adding meaningful semantics. However, it does not describe the optional 'platform' parameter or elaborate on the structure of the 'arguments' object, leaving some ambiguity.

  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: 'Read-only evaluation of MCP tool name and arguments against Blekline workspace tool policy (allow, mask, or block).' It specifies the verb (evaluate), the resources (tool name and arguments), and the intended outcome (policy decision). This distinctively separates it from sibling tools like classify_risk or simulate_policy.

  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 the tool is used when needing to check a tool call against Blekline policy, but it does not explicitly state when to use it over alternatives or mention any exclusions. Sibling tools suggest related functions, but the description gives no comparative guidance, so the usage context is only implicitly conveyed.

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

• blekline_emit_eventA
  3.9/5.0
  Behavior4/5

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

  The description adds 'metadata-only' and 'does not store raw prompt content', providing meaningful behavioral disclosure beyond the annotations' readOnly/destructive hints. The deprecation notice also signals lifecycle status, but it does not mention permissions or 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?

  The description is two short sentences, with the deprecation notice front-loaded and the purpose stated directly. Every word contributes value, and there is no redundant or filler content.

  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?

  Despite having five parameters and no output schema, the description omits any explanation of parameter usage or expected behavior. While the deprecation notice mitigates the need for full documentation, the description remains incomplete for an agent that might need to invoke it.

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

  Parameters1/5

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

  The description provides no information about any of the five parameters (kind, action, platform, riskTier, entitiesMasked). With 0% schema description coverage, the description fails to add any meaning beyond the bare schema, which itself lacks 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 the tool writes a metadata-only governance audit event to the Blekline workspace, using a specific verb and resource. It distinguishes itself from siblings by explicitly marking itself as deprecated and naming the replacement tool, blekline_log_governance_event.

  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 opens with '[Deprecated — use blekline_log_governance_event]', which is an explicit directive to use the alternative tool. It also clarifies the intended use case (metadata-only events, no raw prompt content), giving strong context for when to use or avoid this tool.

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

• blekline_mask_promptA
  4/5.0
  Behavior3/5

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

  Annotations only set readOnlyHint=false and destructiveHint=false, which convey little. The description adds the context of an external 'Blekline control plane' and the pre-LLM position, but it does not disclose whether the operation has side effects, what the response looks like, or failure modes. This is partial transparency beyond 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 a single, front-loaded sentence that states the action, target, and context. Every word earns its place with no redundancy or filler.

  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 two-parameter tool with no output schema, the description adequately covers purpose and context. It does not state the return value or mention error conditions, but given the straightforward nature and clear sibling differentiation, it is reasonably complete.

  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 input schema has 100% coverage with descriptions for both 'text' and 'platform'. The description adds minimal value beyond restating that text is prompt text and does not enrich the 'platform' parameter. Baseline 3 is appropriate since the schema carries the heavy lifting.

  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 'Mask', identifies the resource ('PII and secrets in prompt text'), and adds process context ('via the Blekline control plane before sending content to an LLM'). This clearly differentiates it from sibling tools that handle policy simulation, event logging, tool evaluation, risk classification, and event emission.

  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 clearly implies when to use the tool: before sending content to an LLM. It provides the context of a preprocessing step but does not explicitly state when not to use it or mention alternatives. This meets the 'clear context, no exclusions' criterion.

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

• blekline_simulate_policyA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this while adding the crucial detail that content is neither masked nor persisted. This goes beyond the annotation metadata by clarifying the tool's non-mutating, non-logging behavior. It does not describe the exact output format, but for a read-only simulation the safety profile is well 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?

  A single, tightly worded sentence that delivers the essential purpose and behavior without unnecessary words. Every phrase earns its place: read-only, simulation, no masking, no persistence.

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

  Completeness3/5

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

  Given the tool's simplicity and the annotations, the description covers the core behavior but leaves gaps. There is no output schema, and the description does not indicate what the simulation returns (e.g., policy decisions, risk scores), which an agent would need to decide whether to invoke the tool. Parameter details for platform and sourceHost are also absent. The tool is still usable, but the description is not fully self-sufficient.

  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 only mentions the 'prompt' by name indirectly ('on a prompt'). It does not explain the meaning or purpose of the 'platform' and 'sourceHost' parameters, which are likely important for policy simulation context. The description fails to compensate for the lack of 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 it is a read-only simulation of a redaction policy on a prompt, explicitly noting no masking or persisting occurs. This distinguishes it from siblings like blekline_mask_prompt (which applies masking) and logging tools. The verb 'simulate' is 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 Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the intended use case: dry-run evaluation of policy without side effects. It contrasts with masking/persisting tools, giving context for when to choose simulation over alternatives. However, it does not explicitly name alternatives or provide exclusionary guidance, so it stops short of a 5.

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

• blekline_classify_riskA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds that it performs no masking and persists no content, which is extra context. It also flags deprecation, which is valuable for the agent. However, it does not describe output format or error behavior, so it falls short of a 5.

  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 one compact sentence, front-loads the deprecation notice, and wastes no words. It effectively communicates the essential information.

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

  Completeness3/5

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

  Given the tool is deprecated and has no output schema, the description covers the most critical information (deprecation and read-only nature) but omits return values and the meaning of platform/sourceHost. It is adequate for a deprecated tool with a clear successor, but not fully complete for someone who might still invoke it.

  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 only vaguely references 'a prompt' without explaining the platform or sourceHost parameters. It does not compensate for the schema's lack of descriptions, leaving these parameters semantically unclear.

  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 states a specific verb ('simulates') and resource ('Blekline redaction policy on a prompt'), and distinguishes from siblings by noting it is read-only and does not apply masking or persist content. It also explicitly names the successor tool.

  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 '[Deprecated — use blekline_simulate_policy]', providing a clear directive for when to use the replacement tool. It also implies when this tool might have been used (read-only simulation without masking) versus alternatives like blekline_mask_prompt.

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