Server Quality Checklist

Tool Scores

• configure_policyC
  2.8/5.0
  Behavior2/5

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

  Annotations include only readOnlyHint=false, which indicates a write operation, and the description's 'Configures or updates' confirms mutation. However, the description does not disclose side effects such as whether existing rules are overwritten, whether the change is reversible, permission requirements, or any validation behavior. With minimal annotation coverage, more transparency is needed.

  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?

  The description is a single concise sentence with no redundancy. However, the phrase 'parameter A' is vague and under-specified, making the sentence less useful than its brevity suggests. It is economical but not fully informative.

  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?

  This is a mutation tool with 6 parameters, nested objects, and an output schema, yet the description provides almost no contextual guidance beyond the basic action. The agent is left to infer update semantics, failure modes, and how the complex policy fields relate to one another. The output schema reduces the need to explain return values, but the description still lacks sufficient context 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?

  Schema description coverage is 100%, so each of the 6 parameters is already documented in the input schema. The description adds no parameter-level meaning beyond that, which matches the baseline scenario where the schema carries the burden. No deduction is warranted, but no additional value is added either.

  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 states a specific verb ('Configures or updates') and a resource ('Enterprise Custom Policy rules'), which distinguishes it from the listed siblings at a high level. However, 'parameter A' is an unexplained placeholder that weakens clarity and would confuse an agent.

  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, nor any exclusions or prerequisites. The sibling tools appear unrelated, so while confusion is unlikely, the agent receives no context about typical scenarios, sequencing, or whether this tool should be used before/after other operations.

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

• evaluate_fdiaB
  3.2/5.0
  Behavior3/5

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

  The readOnlyHint annotation already signals a non-mutating operation. The description adds some value by stating the evaluation is deterministic and exposing the equation F = (D^I) * A, but it does not explain what F represents, how failures are handled, or what side effects may occur.

  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 a single dense sentence with no filler and front-loads the core purpose. However, the formula and 'enterprise custom policy rules' feel under-explained for an agent that may need to act on the result.

  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?

  With full schema coverage, an output schema, and readOnlyHint annotation, the structural context is strong. Still, the description lacks usage guidance and does not explain the meaning or consequence of F, leaving some ambiguity about what an agent should do with the result.

  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%, so the schema already documents all parameters. The formula adds a cross-parameter relationship hint, but the description does not provide materially new parameter semantics beyond what each field's description already states.

  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 tool evaluates action requests and distinguishes it through the specific ZK-FDIA formula and enterprise custom policy rules. It is not a tautology, though it does not explicitly contrast with sibling tools like configure_policy.

  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 about when to use this tool versus alternatives, what conditions are required, or when not to use it. The description implies an evaluation context but leaves the agent to infer appropriate usage.

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

• orchestrate_swarmB
  3.2/5.0
  Behavior3/5

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

  The description adds behavioral detail beyond the readOnlyHint annotation by revealing that objectives are wrapped into JITNA packets and distributed across Router, Guardian, Executor, and Scribe agents. It does not explain whether coordinating these agents has side effects, but it does not contradict the readOnlyHint.

  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 a single dense sentence that front-loads the core action and lists the involved agents without padding. Some jargon like 'JITNA packets' and '1+4' is unexplained, but the length is appropriate.

  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 output schema, nested objects, and annotations, the description is adequate but high-level: it does not explain JITNA packets, how to set readiness/context parameters, or how the tool relates to sibling tools. An agent could call it correctly from the schema, but the description leaves moderate ambiguity about orchestration semantics.

  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%, so the schema already documents all four parameters. The description adds only conceptual context (agent pillars) rather than parameter-specific details such as how data_readiness or context_params affect orchestration, so it stays at the baseline.

  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 names the action (encapsulates objectives into JITNA packets) and the resource (objectives) while listing the specialized agents involved. It is more specific than the tool name alone, though it does not explicitly differentiate from sibling tools or explain what JITNA packets are.

  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 explicit statement about when to use orchestrate_swarm versus siblings such as evaluate_fdia, configure_policy, rct_think, or compress_context. The schema implies it is for high-level objectives requiring decomposition, but the description itself gives no selection criteria or exclusions.

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

• rct_thinkA
  3.5/5.0
  Behavior3/5

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

  The readOnlyHint annotation already establishes this as a non-destructive operation, lowering the bar for behavioral disclosure. The description adds the claim that it executes a specific mental process to reduce hallucination, but it does not clarify what the tool actually returns, how the 7 stages behave, or whether it produces intermediate reasoning. No contradiction with annotations 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, front-loaded sentence with no redundant clauses. Every phrase contributes to identifying the tool's function and purpose, though 'authentic' and 'mental OS' are slightly stylistic rather than purely informational.

  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 presence of an output schema and the readOnlyHint annotation covers some missing return and safety details. Still, the description leaves ambiguity around what '7-Stage Reverse Component Thinking' actually involves and how it should be invoked in practice, given that the sibling tools suggest a wider workflow 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 description coverage is 100%, so the input schema fully documents all three parameters including their optional/required status and role. The tool description itself does not elaborate on parameter usage or relationships, so it adds no value beyond the schema, but none is strictly required given the coverage.

  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 uses a specific verb ('Executes') and names a distinct resource ('Delentia 7-Stage Reverse Component Thinking mental OS'), making its core function recognizable as a structured reasoning/thinking tool. It also frames the intended effect ('eliminate hallucination'), though the phrasing is somewhat abstract and does not explicitly differentiate it from siblings like evaluate_fdia or compress_context.

  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 through 'eliminate hallucination' and the problem_statement schema description ('complex query, or dilemma requiring rigorous reverse deconstruction'). However, there are no explicit when-to-use/when-not-to-use instructions or references to alternative tools, leaving the agent to infer the appropriate selection.

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

• compress_contextA
  4.3/5.0
  Behavior4/5

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

  The description goes beyond the readOnlyHint annotation by disclosing the compression mechanism and the expected reduction range (74.2%–91.5%). It also implies that non-state-delta content is discarded, which is useful behavioral context, though it could more explicitly state that the operation is lossy or irreversible.

  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, information-dense sentence with no filler. It front-loads the primary action and includes a measurable outcome, making every word valuable.

  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?

  The output schema covers return structure, annotations cover mutation safety, and the schema fully documents all three parameters. For a straightforward compression tool, the one-sentence description plus structured metadata is sufficient for an agent to select and invoke it 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?

  Schema description coverage is 100%, with each parameter already documented in the input schema. The description adds no param-specific detail, so the baseline score of 3 is appropriate.

  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 ('Compresses'), names the resource ('verbose conversation history'), and explains the mechanism ('extracting state deltas'). The token-reduction range adds concrete clarity and differentiates it clearly from sibling tools like evaluate_fdia or orchestrate_swarm.

  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 'verbose conversation history' provides clear context for when this tool applies. It does not explicitly state when not to use it or mention alternatives, but no sibling tool serves the same compression purpose, so the omission is minor.

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