Server Quality Checklist

Tool Scores

• get_problemA
  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 carries full burden. It discloses that the tool returns sparks with idea, next step, and outcome, but omits whether this is a read-only operation, any authentication needs, or side effects. The 'long-running memory' metaphor adds context but insufficient detail.

  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 sentence that effectively communicates the main action and value. It is front-loaded with 'Show one problem plus every spark', though the sentence is somewhat lengthy with parenthetical explanations.

  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 simple schema (one integer parameter, no output schema) and the context of sibling tools, the description provides adequate information about the return value (problem + sparks). It is complete enough for an agent to understand what the tool does.

  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% with one required parameter 'id' described as 'Problem id'. The description adds no extra meaning beyond the schema, so baseline 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 clearly states 'Show one problem plus every spark... captured against it', specifying the verb 'Show' and the resource 'problem' with its history. It distinguishes itself from sibling tools like list_problems (which likely lists without details) and capture_spark (which adds) by focusing on a single problem with full spark history.

  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 this tool is for viewing a problem's accumulated sparks across sessions, but does not explicitly state when to use it versus alternatives like list_problems or evoke. No guidance on exclusions or prerequisites.

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

• capture_sparkA
  3.8/5.0
  Behavior2/5

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

  No annotations provided; description states it persists data but omits behavioral details like idempotency, side effects, or any destructive actions. With no annotations, the description should disclose more about the operation's nature.

  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 wasted words, front-loaded with the core action and context. Efficient and clear.

  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?

  Effectively explains the tool's role in the workflow (evocation output, session memory) but does not describe return values or error behavior. Adequate given no output schema but could include completion signals.

  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%, providing detailed explanations for each parameter. The tool description adds no extra meaning beyond the schema, so 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?

  Description clearly states the verb 'persist' and the resource 'candidate solution plus a concrete next step', and distinguishes from siblings like 'evoke' by positioning it as the output of a successful evocation.

  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 context on when to use (after successful evocation) and the long-running issue progression use case, but does not explicitly exclude scenarios or compare with sibling 'update_spark'.

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

• evokeA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It mentions returning output but does not disclose whether the tool has side effects, requires authentication, or has rate limits. It is moderately transparent but could be more explicit.

  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: first defines action and output, second gives usage guidance. Every sentence is necessary and front-loaded. No redundancy or wasted words.

  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 simplicity (2 params, no output schema, no enums, no nesting), the description covers the core purpose, usage context, and return value. Lacks explicit mention of non-destructive behavior but is still complete enough for an agent to use 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 coverage is 100%, so the baseline is 3. The description adds some context by framing the 'trick' parameter as a general insight, but does not go beyond what the schema already provides in terms of meaning.

  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 action ('Give it a trick...') and the return value ('open problems plus a scaffold'), and it differentiates from siblings like add_problem or list_problems by focusing on testing a generalization against problems.

  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?

  Explicitly says 'Call this whenever you learn something that might generalize,' providing clear when-to-use guidance. Does not explicitly state when not to use, but the context from sibling tools implies alternatives.

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

• add_problemA
  4.2/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Discloses that the problem becomes part of a global set and that the set should be kept small. Does not cover idempotency or error handling, but is adequate for a simple additive operation.

  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, front-loaded with purpose and usage constraint. Every sentence adds value; no waste.

  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?

  Adequate for a creation tool with well-described schema. Covers purpose and usage constraint. No output schema, but return value not critical. Missing details like duplicate handling or error conditions.

  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 describes all 4 parameters with full coverage (100%). Description adds no additional semantic meaning to individual parameters beyond the schema descriptions.

  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?

  Clear verb 'add' and resource 'problem to your global Feynman set'. Distinct from siblings like capture_spark (capture spark) and list_problems (list).

  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?

  States when to use: for long-running problems to keep in mind. Implies not for transient ideas. No explicit exclusions or alternatives named, but the constraint 'keep the active set small' provides guidance.

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

• list_problemsA
  4.2/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It explains the tool shows problems but does not explicitly state it is read-only or describe side effects. For a list tool, this is adequate but could be more transparent.

  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 wasted words, purpose front-loaded. Every sentence adds value.

  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 a single optional boolean parameter and no output schema, the description is reasonably complete. It could mention the return format but is sufficient for a simple list 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?

  Schema coverage is 100% with one boolean parameter. Description adds value by clarifying the default behavior ('Defaults to open ones only') which is not explicitly stated in the schema description.

  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 specific verb 'Show' and resource 'global set of long-running problems', clearly distinguishing it from sibling tools like add_problem, get_problem, and update_spark.

  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?

  Description states default behavior ('Defaults to open ones only') and implies when to use the optional parameter includeClosed. No explicit when-not or alternatives mentioned, but context is clear.

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

• update_sparkA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It explains the meaning of cost, value, and status fields, and stresses that value should be 0 for failures. It does not mention side effects or auth needs, but the behavioral context is well-addressed.

  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 focused paragraph of about 4-5 sentences, front-loading the main purpose then emphasizing failure logging. Each sentence adds value; no wasted words.

  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 5-parameter tool with no output schema, the description covers purpose, usage guidelines, and parameter semantics well. It lacks return value info but that is not critical here. Completeness is high.

  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%, but the description adds significant meaning: clarifies cost as 'ACTUAL effort spent', value as 'graded payoff' (0 for failures), and explains the importance of recording failures. This goes beyond schema descriptions.

  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 title 'Record a spark's outcome' and description clearly state the tool's purpose with specific verb and resource. It distinguishes from siblings like capture_spark (new spark capture) and evoke (retrieval) by focusing on outcome recording.

  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 explicitly guides when to use the tool: after acting on a spark. It strongly emphasizes logging failures, providing rationale ('most bets fail'). No explicit alternatives, but context is clear.

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