Server Quality Checklist

Tool Scores

• saihm_statusA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It discloses that no plaintext is returned, which is a meaningful privacy guarantee. However, it does not explicitly state that the tool is read-only or has no side effects, though 'status' implies this. Adequate but not comprehensive.

  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 core purpose and key details without any unnecessary words. It is perfectly concise.

  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 status tool with no parameters and no output schema, the description provides enough context: what fields are returned and an important privacy constraint. It could elaborate on the meaning of 'tier' or 'custody', but this is adequate for the tool's complexity.

  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, and schema coverage is 100% by default. The description does not need to explain parameters, so the baseline of 4 applies.

  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?

  Description clearly states this tool provides status information (tier, active memory count, custody) and is distinct from the memory-operation siblings (remember, recall, forget). The lack of an explicit verb like 'returns' is minor, but the intent is unambiguous.

  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?

  Usage context is implied by the tool's status nature and sibling names, but there is no explicit guidance on when to use this versus alternatives. It does not mention exclusions or when not to use it, leaving the agent to infer.

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

• saihm_recallA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the load. It adds useful context with 'decrypted client-side', suggesting a secure read operation. However, it does not disclose return format, pagination, or error behavior, leaving some gaps.

  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, front-loaded sentence that conveys the core purpose and optional filtering with no redundant 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?

  This is a simple recall tool with one optional param and no output schema. The description states the core function and decryption behavior but does not describe the return format or edge cases, which would be expected without an output schema. It is minimal but adequate.

  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 already describes the 'query' parameter as an optional keyword filter, and the description echoes this. With 100% schema coverage, no additional parameter semantics are provided, so baseline of 3 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 uses the specific verb 'Recall' with the resource 'SAIHM memories' and mentions optional keyword filtering, clearly distinguishing it from sibling tools like remember/forget/status.

  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 context clearly implies use for retrieving memories, while siblings handle other operations, but it does not explicitly name alternatives or exclusions. The guidance is adequate though not exhaustive.

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

• saihm_rememberA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses a non-obvious behavioral trait ('sealed client-side before it leaves this process') and explains the update mechanism via cellId. However, it does not mention success/failure behavior or side effects like overwriting content.

  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, no filler. The core action is front-loaded, and the update instruction is concise. 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?

  The tool is simple (2 params, no output schema, no annotations), and the description covers the essential purpose, update behavior, and a key security trait. Missing return value info is acceptable for a store operation given the low complexity.

  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%, so the baseline is 3. The description adds no new meaning beyond the schema: 'Pass cellId to update an existing memory' mirrors the schema's parameter description. Content is simply 'The text to remember' without additional context.

  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+resource ('Store a memory in SAIHM') and clearly distinguishes from siblings by noting the update capability via cellId. This makes the tool's purpose unambiguous and distinct from recall/forget/status.

  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 storing new memories or updating existing ones, but does not explicitly state when to use this tool versus alternatives like saihm_recall or saihm_forget. No exclusions or alternative recommendations are provided.

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

• saihm_forgetA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries full responsibility. It explicitly states 'permanently', 'irreversible', and 'GDPR Art. 17 erasure', which discloses the destructive, non-recoverable nature. It does not cover edge cases like non-existent cellId or authorization requirements, but it transparently conveys the primary behavioral trait.

  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 entire description is one sentence, front-loaded with the action ('Permanently crypto-shred') and includes critical caveats (irreversible, GDPR). No wasted words, perfectly concise.

  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 simple single-parameter destructive tool, the description covers purpose, irreversibility, and legal reference. No output schema is needed, and the parameter is explained. The tool is adequately specified for an agent to invoke correctly.

  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 0%, so the description must supply parameter meaning. The phrase 'by cellId' clarifies that the sole parameter is the identifier of the memory to erase, which is more semantic than the schema's bare 'string' type. It does not specify format or validity rules, but the parameter's purpose is sufficiently clear.

  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 the specific verb 'crypto-shred' and specifies the resource as 'a memory by cellId', clearly indicating a delete/erase operation. This distinguishes it from siblings like 'saihm_remember' (store), 'saihm_recall' (retrieve), and 'saihm_status' (query state).

  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 this is the tool for permanent deletion and provides legal context (GDPR Art. 17), but it does not explicitly mention alternatives or when-not-to-use. Sibling names reinforce its role, giving clear contextual usage.

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