Server Quality Checklist

Tool Scores

• system_controlD
  1.9/5.0
  Behavior1/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It only offers a minor note about status showing CAGEERF phase context, without disclosing any actions, side effects, or persistence behaviors inherent to system administration.

  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 extremely brief, but the brevity results in under-specification rather than effective conciseness. The single vague sentence adds little value beyond the tool's name and does not earn its place.

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

  Completeness1/5

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

  With 11 parameters, no annotations, and no output schema, the description must provide substantial context but only gives a vague one-liner. It fails to explain the tool's operations, supported actions, or expected behavior, making it inadequate for safe invocation.

  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 provides descriptions for all 11 parameters, achieving 100% coverage. The tool description adds no additional parameter semantics, so the baseline score of 3 applies.

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

  Purpose2/5

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

  The description states 'System administration' and 'Status shows current CAGEERF phase context,' which is vague and largely restates the tool's name. It fails to specify any concrete verb or resource and does not differentiate from sibling tools like prompt_engine or resource_manager.

  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 guidance is provided on when to use this tool versus alternatives. There is no mention of use cases, prerequisites, or exclusions, leaving the agent without criteria for selecting this tool.

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

• resource_managerB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description must carry the full burden of disclosing behavioral traits. It mentions CRUD and a few action constraints (e.g., switch is framework-only), but does not describe side effects such as destructive deletes, persistence, versioning, or consequences of reload/rollback/clear. Many actions from the schema are absent, so the agent remains unaware of their 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 exceptionally concise and well-structured, with a clear title, usage line, resource types, actions, and a single special-case instruction. Each line adds necessary information without filler, and the layout makes it easy to scan.

  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 the tool's complexity (41 parameters, 14 actions, 4 resource types), the description is far from complete. It omits the 'checkpoint' resource type and advanced actions such as analyze_type, analyze_gates, history, rollback, compare, and clear. No output schema exists, so the description should cover more of the tool's capabilities.

  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 schema has 41 parameters with zero description coverage, so the tool description must compensate. It does clarify resource_type by defining prompt, gate, and framework, and it explains some action constraints, but the overwhelming majority of parameters (id, name, gates, limit, version, etc.) remain undocumented. The description only partially addresses the required 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 immediately establishes a specific purpose: 'Unified CRUD for prompts, gates, and frameworks.' It names concrete resource types and lists actions, making it clear this is a management tool for these entities. The title and usage string further reinforce the verb-resource relationship.

  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 a usage template and enumerates resource types and actions, giving clear context for how to invoke the tool. However, it does not explicitly state when to choose resource_manager over sibling tools like prompt_engine or system_control, nor does it mention when not to use it. The special case for action:'guide' is a helpful guideline but limited.

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

• prompt_engineA
  4.1/5.0
  Behavior4/5

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

  Despite no annotations, the description discloses key behavior: it returns instructions rather than executing phases itself ("WHAT YOU DO: Execute each phase yourself"). It also details retry limits, presets, modifiers, and shell validation behavior, which go beyond the structured schema.

  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 moderately long but well-organized into sections (WHAT IT RETURNS, WHAT YOU DO, SYNTAX, PRESETS, MODIFIERS). Each section contributes practical usage information with minimal waste, though it could be tightened.

  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 (8 params, nested objects, no output schema), the description covers the overall workflow, syntax, chaining, validation, presets, and modifiers. It does not explicitly explain the resume parameters (chain_id, gate_verdict, user_response) but the schema descriptions cover those, so the description adds sufficient context.

  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 baseline is 3. The description adds high-level syntax context (e.g., >>prompt_id, :: verify) but does not map those directly to the named parameters or add per-parameter meaning beyond the schema's own descriptions. It introduces concepts like verify and presets that don't correspond clearly to schema fields.

  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 verb and resource: "Execute prompts with C.A.G.E.E.R.F framework and ground-truth validation." It defines what it returns (prepared prompt + phase instructions) and what the agent should do, making it distinct from sibling tools like system_control and resource_manager.

  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 gives clear context on when to use the tool (for executing prompts with CAGEERF and validation) and how to invoke it via syntax examples. It does not explicitly name alternatives or exclusions, but the purpose is specific enough that selection is unambiguous.

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