Server Quality Checklist

Tool Scores

• decisio_devils_advocateA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must fully disclose behavioral traits. It fails to state that this is a read-only analysis, what the output format is, or whether there are prerequisites (e.g., a prior decision must exist). The lack of such details leaves the agent uncertain about side effects and expected results.

  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 sentences, front-loaded with the primary action, and every word adds value. It efficiently communicates the tool's purpose without redundancy.

  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 tool is simple (one parameter, no nested objects, no output schema), and the description covers the core purpose. However, it omits details about return values or any side effects, which is a notable gap given the absence of an output schema. It is adequate but not fully 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?

  Schema description coverage is 100% with the only parameter 'decision_id' described as 'Decision ID from decisio_create_decision.' The description adds no parameter-specific detail, but since the schema fully documents the parameter, a 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 'Challenge' and names the target resource ('the winning option'), clearly stating the tool's function. It also distinguishes itself from siblings by focusing on runner-up analysis and sensitivity to result flipping, which is distinct from comparison or calculation tools.

  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 after a decision has been made, as it refers to 'the winning option' and 'the runner-up,' but it does not explicitly state when to use this tool versus alternatives. No exclusions or conditions are provided, leaving the context somewhat implicit.

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

• decisio_create_decisionA
  3.6/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It says 'Start' but does not disclose whether the decision is persisted, what the return value is, or any side effects. It also does not explain how templates interact with provided options or criteria.

  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 main action and then explains how to use it. No wasted words.

  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 no output schema and no annotations, the description is incomplete for a creation tool. It does not mention return values, whether the decision is saved, or what steps follow creation. The template list is present but not linked to the rest of the workflow.

  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 100%, so baseline is 3. The description adds value by clarifying that you can provide criteria and options OR use a template, which simplifies the relationship between parameters that the schema describes more technically.

  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 purpose with a specific verb and resource: 'Start a new AHP decision analysis.' This distinguishes it from siblings like compare, calculate, and list_templates, 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 explains the primary use case and the option to use a template, but it does not explicitly mention when to choose this tool over siblings or provide exclusions. Usage context is implied rather than explicit.

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

• decisio_compareA
  3.7/5.0
  Behavior2/5

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

  With no annotations, the description carries full burden for behavioral disclosure. It mentions the action 'set' but does not reveal whether existing comparisons are overwritten, how duplicates are handled, or any side effects. The value scale is already in the schema, so the description adds no new behavioral context.

  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 sentences, immediately states the action, and gives precise conditional instructions. Every sentence is purposeful with no redundancy or filler.

  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 covers the core usage and conditional parameter semantics, but it omits crucial behavioral details such as whether comparisons are appended or replaced, and how the tool interacts with the overall decision flow (e.g., whether calculate is called separately). This is adequate but has clear gaps for a mutation tool.

  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%, and the schema already describes the value scale and the criterion's conditional usage. The description repeats this information without adding meaningful new detail beyond what the schema provides, so baseline 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 clearly states the verb 'Set' and the resource 'pairwise comparisons for criteria or options', with specific scope on criteria vs options. It uniquely identifies the tool's function among siblings like calculate or create_decision, even without naming them.

  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 provides clear usage context for two scenarios: criteria comparisons (omit criterion) and option comparisons (provide criterion). While it does not explicitly compare against sibling tools, the directional guidance is sufficient for correct invocation.

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

• decisio_calculateA
  4/5.0
  Behavior3/5

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

  No annotations provided, so the description carries the full burden. It describes the return values and the behavior with partial data. However, it does not disclose any side effects, permissions, or error conditions, leaving some uncertainty about the tool's operational 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?

  Two sentences, direct and efficient. The key action and outputs are front-loaded.

  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 (one parameter), and the description covers the essential aspects: what it does, what it returns, and its behavior under partial data. No output schema exists, but the return values are named. Some edge cases are not addressed, but for this simple tool, 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 schema already documents decision_id as coming from decisio_create_decision, and the description doesn't add further parameter details. Since schema coverage is 100%, the 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 clearly states the tool runs AHP calculation on a decision, with specific outputs (ranked options, criteria weights, consistency check). This distinguishes it from siblings like decisio_compare or decisio_quick_decide, which target different decision processes.

  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?

  Provides clear context: 'Works best when all pairwise comparisons are set, but will produce results with partial data.' This tells when to use the tool, though it doesn't explicitly mention alternatives or when to avoid it.

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

• decisio_list_templatesA
  4.2/5.0
  Behavior3/5

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

  The word 'List' signals a read-only operation, and the mention of returning criteria/options gives some behavioral insight. However, with no annotations, the description does not explicitly state that it makes no changes, nor does it disclose any rate limits or other runtime behavior. More explicit transparency would be beneficial.

  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 leads with the action word and packs in the key information: what is listed and what those items contain. There is 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, parameterless list tool, the description adequately covers the necessary information: it states the output (templates) and the content included (default criteria and options). It does not discuss formatting or ordering, but these are unlikely to be essential for such a straightforward tool.

  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 accepts no parameters, so the description is not required to explain parameter semantics. The baseline for 0-parameter tools is 4, and the description adds no confusion about inputs.

  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 direct verb 'List' and clearly identifies the resource as 'available decision templates' with their default criteria and options. This differentiates it from siblings that create, compare, calculate, or advise, making its function unmistakable.

  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 usage context: when you need to see available templates before creating a decision. It is clear but does not explicitly mention alternative tools or exclusion scenarios, 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.

• decisio_quick_decideA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries full disclosure burden. It communicates the atomic single-call nature, the need for complete upfront input, and the immediate ranked output. It does not cover error handling or consistency checks, but for a computation tool these are minor 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?

  The description is four short sentences, each serving a distinct purpose: what it does, what to provide, when to use it, and what you get. No redundant or filler content.

  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 has moderate complexity with 5 required parameters but no output schema. The description adequately covers the operational context (single call, complete inputs), the use case, and the return value (ranked results). It is slightly vague about the exact output structure, but the schema documents inputs thoroughly.

  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 covers all parameters with examples and descriptions (100% coverage), so the baseline is 3. The description adds no additional parameter-level detail beyond restating the required inputs and emphasizing 'ALL pairwise comparisons,' which the schema already conveys.

  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 opens with a clear verb and object ('Run a complete AHP analysis'), specifies the input requirements ('goal, criteria, options, ALL pairwise comparisons'), and differentiates itself from step-by-step siblings by emphasizing single-call execution and immediate ranked results.

  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?

  It explicitly states the primary use case ('Best for when you already know all the comparisons'), implying it should be avoided when comparisons are not fully known. It does not name specific alternative tools or state exclusions, so it stops short of a fully explicit when/when-not.

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