Server Quality Checklist

Tool Scores

• lucho_plan_treasuryB
  3.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description reinforces this by stating the tool never executes a financial action. It also discloses the internal workflow (computed liquidity, scoring, stress-testing) and the three possible returned verdicts, which is meaningful behavioral context beyond the annotations.

  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 compact and front-loaded: the core process and decision output appear in one sentence, and a second sentence clarifies the tool's non-executing nature. Every phrase earns its place with no repetition of the title or schema.

  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?

  The tool has high complexity — nested goal/balance/products objects, four top-level parameters, no output schema, and related siblings — but the description only summarizes high-level steps. It omits guidance on required parameter relationships, sourceMode semantics, constraints, or how this planning tool relates to the sibling tools, leaving agents to guess for realistic invocations.

  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?

  Schema description coverage is 0%, and the description provides virtually no parameter-level guidance. It only contextualizes 'products' as Binance earning products and implies an 'allocation,' but leaves goal, balance, sourceMode, and all nested field semantics unexplained. Given the large nested schema, some compensation was needed and is mostly absent.

  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 a specific sequence of actions — calculate protected liquidity, score normalized Binance earning products, stress-test the allocation — and states the exact decision output (ALLOCATE, HOLD, or BLOCK). This clearly differentiates the tool from simple crud or execution tools, though it does not explicitly distinguish it from sibling planning/verification tools.

  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?

  The description implies use for planning and simulation, especially via 'This tool never executes a financial action,' but it does not state when to choose this tool over lucho_tighten_plan, lucho_verify_stress, or lucho_create_receipt. No when-to-use, when-not-to-use, or alternative routing is provided.

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

• lucho_verify_stressB
  3.3/5.0
  Behavior4/5

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

  The description reinforces and expands on the readOnly/idempotent annotations by stating that the tool never executes a financial action, which is a useful safety clarification. It also specifies the two types of checks performed (liquidity and rate-drop), adding behavioral context beyond the annotations. No contradiction with annotations is present.

  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, focused sentences with no fluff. The core purpose is front-loaded in the first sentence, and the safety guarantee is clearly stated in the second. Every word contributes meaning.

  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 high complexity of the nested input schema, the absence of an output schema, and zero parameter documentation, the description is too sparse to fully equip an agent. It covers the tool's high-level purpose and that it is read-only, but leaves critical questions unanswered about what inputs mean, what constitutes success or failure, and what the tool returns.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%: none of the four complex parameters (goal, balance, allocations, products) are described in the schema or the tool description. The description gives no guidance on what values to supply, what they mean, or how they relate to the stress checks. An agent would have to infer the semantics purely from the property names and nested structure.

  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 a specific verb ('Re-run'), a clear resource ('mandatory liquidity and rate-drop stress checks for a proposed plan'), and explicitly states that the tool never executes a financial action. It conveys the tool's role among planning-related siblings, though it does not explicitly name an alternative tool for contrast.

  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 phrase 'for a proposed plan' and 'Re-run' imply the tool should be used after a plan has been created, when verification or re-verification is needed. However, it does not explicitly say when to prefer this tool over lucho_tighten_plan, lucho_plan_treasury, or lucho_create_receipt.

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

• lucho_tighten_planB
  3.4/5.0
  Behavior4/5

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

  Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond these: the operation can only reduce allocations or veto products, and it cannot increase the deterministic plan. This is a non-obvious invariant that helps an agent predict effects, though it does not describe return behavior or persistence details.

  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?

  A single sentence with no filler: it states the operation, the actor, and the critical invariant front-loaded. Every clause earns its place, and it is far shorter than the schema while adding the most important behavioral rule.

  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?

  With five parameters, a nested plan object, and no output schema, an agent needs more than this description to invoke the tool correctly. The description does not define the deterministic plan, explain how to express reductions versus vetoes, differentiate the sibling tools, or describe the output. The monotonicity constraint is useful but not sufficient for full context.

  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?

  Schema description coverage is 0%, and the description provides almost no parameter-level meaning. It only hints at allocations and product vetoes at a high level, leaving plan.decision, vetoProductIds, amountByProduct, maxTotalAllocation, and rationale unexplained. The schema's structural names carry some meaning, but the description does not compensate for the zero-coverage gap.

  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 ('Apply'), a resource ('critic decision' to an allocation plan), and a clear constraint: it may only reduce allocations or veto products, never increase the deterministic plan. This is specific enough to differentiate from the sibling tools by behavior, though it does not explicitly name alternatives.

  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 phrase 'Apply a critic decision' implies this tool is for incorporating critic feedback into an existing plan, and the monotonicity constraint clarifies when it applies. However, there is no explicit statement of when to use this tool versus siblings such as lucho_plan_treasury or lucho_create_receipt, nor any 'when not to use' guidance.

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

• lucho_create_receiptA
  4/5.0
  Behavior4/5

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

  Beyond the readOnlyHint annotation, the description adds meaningful behavioral context: the operation is only a receipt-creation step, not plan execution, and the receipt is fingerprinted and credential-safe/redacted. No contradiction found between the 'create' wording and readOnlyHint, since the receipt can be interpreted as a returned artifact rather than a persisted side effect.

  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 with no wasted words. The core purpose is front-loaded, and the critical 'does not execute' clarification follows immediately.

  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 takes a complex nested plan and has no output schema, yet the description says nothing about how mode affects behavior, what the returned receipt contains, or how it should be used downstream. The input schema provides structure, but some operational context is missing.

  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?

  Schema description coverage is 0%, so the description bears the burden of explaining parameters, but it does not explain 'mode' or 'plan' semantics directly. It only implicitly echoes mode values ('fixture, dry-run, or live') and refers to a generic 'plan.' The nested plan schema is rich, but the prose adds almost no parameter-level guidance.

  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 a specific action ('Create'), a specific resource ('fingerprinted, credential-safe receipt'), and the applicable context ('completed fixture, dry-run, or live decision'). It also differentiates from execution/planning siblings by adding 'This does not execute the plan.'

  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 communicates when to use the tool: after a decision has been completed in fixture, dry-run, or live mode. It also gives an exclusion ('does not execute the plan'), though it does not explicitly name alternative sibling tools for planning or verification.

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