Server Quality Checklist

Tool Scores

• memory_deleteC
  2.7/5.0
  Behavior2/5

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

  With no annotations, the description carries full transparency burden. It mentions the protected keys constraint but omits side effects, error cases (e.g., key not found), authorization needs, and the meaning of 'guarded' memory.

  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?

  Two sentences are concise, but the structure lacks organization. The content is front-loaded with the action, but the brevity sacrifices necessary details.

  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?

  Even with an output schema, the description fails to explain successful deletion behavior, error conditions, or the 'guarded' concept. For a delete operation with one parameter, more completeness is expected.

  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 single parameter 'key' has 0% schema description coverage and the description adds no information about its format, source, or allowed values. The agent must infer meaning from the tool name alone.

  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 clearly states the action (delete a key) and the resource (guarded mem9 memory), distinguishing it from sibling tools like memory_list and memory_write.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

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

  No explicit guidance on when to use this tool vs. alternatives (e.g., memory_write or quarantine_list). The only usage hint is the constraint 'Protected keys cannot be deleted,' but this is a behavioral limitation, not a decision guide.

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

• memory_readB
  3.2/5.0
  Behavior4/5

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

  With no annotations, the description effectively discloses key behaviors: integrity verification, outbound screening, potential redaction of sensitive content, and blocking of tampered/policy-violating entries. This helps the agent understand side effects and constraints beyond a simple read.

  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 extremely concise at two sentences, with the primary action in the first sentence. Every sentence adds value, and there is no redundant or irrelevant 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?

  The description adequately covers behavioral aspects, but given the low schema coverage and zero parameter explanations, it feels incomplete. The existence of an output schema partially compensates for missing return value details, but parameter semantics are lacking, which reduces overall completeness.

  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?

  Schema description coverage is 0%, and the description provides no explanation for the 'key' and 'default' parameters. The purpose of 'default' (return value when key is missing) is not mentioned, leaving the agent to infer from the schema alone.

  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 the action ('Read a value') and the target resource ('guarded mem9 memory'). It is specific enough to understand the primary function, but does not differentiate from sibling tools like memory_list, which also reads memory in a different way.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

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

  There is no guidance on when to use this tool versus alternatives. The description explains behavior during reads (integrity verification, redaction, blocking) but does not explicitly state when to choose memory_read over memory_list or other sibling tools.

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

• memory_writeA
  3.9/5.0
  Behavior4/5

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

  Provides good behavioral context: explains that values are screened by agent-memory-guard with possible outcomes (allow/redact/quarantine/block), mentions self-poisoning detection driven by source_class, and describes optional memory_class. Since annotations are absent, the description carries the full burden and does so effectively.

  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 concise—three sentences—with the main action front-loaded. Every sentence earns its place, providing key details without fluff.

  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?

  Covers behavioral traits like screening and provenance, but does not address return values, error handling, or constraints on key/value (e.g., length, format). An output schema exists but is not shown; given no annotations, some gaps in completeness remain.

  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 0%, so the description must compensate. It lists possible values for source_class and gives an example for memory_class, adding meaning beyond schema titles. However, key and value parameters are not described; their roles must be inferred. The description adds value but leaves important gaps.

  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?

  Clearly states 'Write a value to guarded mem9 memory', which is a specific verb and resource. It distinguishes itself from sibling tools like memory_delete, memory_list, memory_read, which are obviously different operations.

  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?

  No explicit guidance on when to use this tool versus alternatives. The description implies it is for storing values, but does not mention when not to use or compare with other memory tools. Usage context is left to inference.

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

• quarantine_listA
  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 burden. It states the tool lists quarantined writes pending review but fails to disclose any behavioral traits such as pagination, ordering, or whether the list is ordered by time. It does not contradict any 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, concise sentence that front-loades the main purpose with no extraneous words. Every word 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 tool has zero parameters and an output schema exists (per context signals), the description is reasonably complete for a simple list operation. However, it could mention ordering or whether pagination is supported.

  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 tool has zero parameters, so per the guidelines baseline is 4. Schema coverage is trivially 100%. The description adds no parameter info, but none is needed.

  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 verb 'List' and the resource 'writes currently held in quarantine', specifying the scope (detected anomalies pending review). This effectively distinguishes it from sibling tools like memory_list or security_events.

  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 for reviewing quarantined writes but provides no explicit guidance on when to use versus alternatives, nor any exclusion criteria. Context from sibling tools (e.g., security_events) is not referenced.

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

• security_eventsA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It indicates a read-only operation ('return recent...') and implies no side effects. The ordering and use case are clear, but there is no explicit mention of safety (e.g., non-destructive), though the verb 'return' suggests safe behavior.

  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 extremely concise: two sentences with no wasted words. It front-loads the core action and provides a concrete use case, making it easy to parse quickly.

  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 has a simple schema (one optional param) and an output schema, the description is mostly complete for understanding the tool's purpose and basic behavior. However, it omits details about the limit parameter and does not explain the output format, relying on the output schema to fill gaps.

  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?

  The input schema has one optional parameter 'limit' with no schema description (0% coverage). The description does not mention this parameter or its effect on results. It fails to add meaning beyond the schema, which is insufficient given the low 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?

  The description clearly states the tool returns recent security events from the guard, ordered newest first. It specifies the resource ('security events') and the action ('return'), and distinguishes from siblings like memory tools and quarantine_list by focusing on auditing logs for actions like blocking, redaction, or quarantine.

  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 explains when to use the tool ('useful for auditing why a write was blocked...'), providing context. However, it does not explicitly state when not to use it or name alternative tools, though the sibling tools are distinct in purpose.

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

• memory_listA
  4.3/5.0
  Behavior4/5

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

  Without annotations, the description carries the full burden. It states it lists keys from 'guarded mem9 memory', hinting at security context. The operation is simple and read-only, so transparency is adequate.

  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 clear sentence with no wasted words. It is front-loaded and efficient.

  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 parameters and the existence of an output schema, the description sufficiently explains the tool's purpose. It does not need to detail return values as those are covered by the output 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?

  There are no parameters, and schema coverage is 100%. With zero parameters, the baseline is 4, and the description adds no parameter info but doesn't need to.

  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 specifies the verb 'list' and the resource 'keys in guarded mem9 memory'. It distinguishes from sibling tools like memory_delete, memory_read, and memory_write, which perform different operations.

  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 for listing stored keys but does not explicitly state when to use this tool versus alternatives. No guidance on when not to use it is provided.

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