Server Quality Checklist

Tool Scores

• boost_desireA
  3.9/5.0
  Behavior3/5

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

  The description explains the mechanism (simulates dopamine response) and the trigger, but does not disclose potential side effects, permanence, or prerequisites for the boost. With no annotations, the description carries the burden, and it only partially fulfills it.

  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?

  Three sentences, front-loaded with the action. The third sentence is somewhat redundant with the first but overall concise and readable.

  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 two-parameter tool, the description gives purpose and trigger but omits return behavior or side effects. No output schema exists, so a bit more detail on the effect would improve completeness, but it remains 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 input schema already provides full descriptions for both parameters, including value meanings for amount and reference to desire_config.json for desire_name. The description adds no additional parameter detail, so baseline 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 boosts a desire level in response to novelty/surprise, using dopamine/prediction error framing. It distinguishes from siblings by focusing on increasing desire due to unexpectedness, whereas satisfy_desire likely reduces/fulfills and get_desires reads.

  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?

  Explicit trigger condition is given: 'Call when you feel surprised or encounter unexpected info.' This gives clear when-to-use guidance. It does not explicitly mention when not to use or alternative tools, so not a 5.

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

• get_desiresA
  3.9/5.0
  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 for behavioral disclosure. While 'Get' implies a read operation, the description does not explicitly state that it has no side effects, how the levels are returned, or any other behavioral traits. The threshold instruction is advisory, not a disclosure of tool 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—two short sentences that front-load the purpose and add a key action threshold. Every word earns its place, with no redundancy or fluff.

  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 simplicity (0 params, no output schema, no annotations), the description covers the core purpose and a usage trigger. However, it omits details about the response format (e.g., how desire levels are presented), which the agent would need to interpret results. Still, it is adequate for a basic read 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 has zero parameters, so the schema coverage is 100% (vacuously). The baseline for 0 params is 4, and the description does not need to explain parameter meaning since none exist. No additional parameter information is required.

  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 function with a specific verb+resource: 'Get current desire levels.' It distinguishes itself from sibling tools (satisfy_desire, boost_desire) by being a read-only retrieval operation, and the threshold instruction adds concrete scope.

  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 'Act immediately on any desire with level >= 0.7' gives clear context for when to use the tool (to check levels) and what to do next (act if threshold met). It implies the need for follow-up actions via sibling tools, though it doesn't explicitly name alternatives or exclusions.

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

• satisfy_desireA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description must carry the full burden. It clearly discloses the core behavioral trait: 'The level drops by 0.4' and that repeated calls are possible. It does not cover error handling or prerequisites, but the essential mutation behavior is 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?

  The description is two short sentences, front-loaded with the action and outcome. Every phrase contributes: the trigger, the parameter, the numeric effect, and the repeat condition.

  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 single-parameter tool with no output schema, the description covers purpose, usage trigger, and effect. It is sufficient, but lacks explicit mention of invalid desire names or return values, so it is not fully complete.

  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 schema already covers the single parameter 100%, so baseline is 3. The description adds meaning by requiring the desire_name to be the one 'you just acted on' and references desire_config.json for valid names, which goes beyond the bare schema.

  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 'satisfy' and identifies the resource 'desire', with a clear effect: 'The level drops by 0.4.' This distinguishes it from sibling tools like boost_desire, which would increase the level.

  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 when to use the tool: 'after taking an action' and 'Pass the desire_name you just acted on.' It also gives a conditional instruction, 'Call again if still high.' It does not name alternatives explicitly, so it misses the top score.

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