Server Quality Checklist

Tool Scores

• list_late_tripsC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of disclosing side effects and read-only nature. It does not state whether the tool modifies data, what happens with missing parameters, or define 'usable trips'. Potential side effects and data safety are ambiguous, given the lack of explicit read-only or mutation statements.

  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 brief and well-structured, consisting of two sentences that introduce the main behavior and a follow-up usage hint. It is concise without unnecessary fluff, though it omits important details that could be added without redundancy.

  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 description provides only minimal context: it references a prior tool and vaguely mentions 'usable trips' and 'late'. It does not explain the output structure, the meaning of parameters, or how to interpret results. Given the schema has 6 parameters and no output schema is shown, the description is insufficient for full understanding.

  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?

  The description only partially explains include_on_time (late vs all trips) but provides no meaning for route, start_date, end_date, limit, or late_threshold_min. The schema gives titles but no descriptions, and the description adds minimal value for most parameters, leaving coverage low.

  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 lists usable trips that are late, with a conditional behavior based on include_on_time. The verb 'list' and resource 'usable trips' are specific, and it references route_otp_summary for context, avoiding tautology. However, it does not explicitly differentiate from other sibling tools beyond the usage hint.

  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 route_otp_summary to drill into trips, providing some situational context. It does not explicitly state when not to use this tool or compare alternatives, so the guidance is implicit rather than explicit.

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

• data_quality_reportA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses a key behavioral nuance: 'Surfaces the MH-12-7781 / OPS-2207 handoff text as a policy question without applying a hidden on-time override.' This clarifies that the tool does not silently alter results. It could add more about side effects or authentication, but as a reporting tool the read-only nature is evident.

  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 sentences, each contributing unique value: the purpose, the explanation of exclusions, the policy question, and the explicit 'no hidden override' behavior. It is front-loaded with the core function and free of 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 read-only reporting tool, the description explains what it does and why, including a specific edge case (the handoff policy question). It omits parameter guidance, which is a gap, but the output schema exists and the overall context is sufficient for an agent to invoke the tool correctly. A 5 would require richer detail on when to use it relative to siblings.

  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% and the description does not mention any of the three parameters (route, device_id, late_threshold_min). It provides no insight into how these optional filters affect the report. Since the description fails to compensate for the complete lack of parameter documentation, the agent must rely solely on parameter names.

  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+resource: 'Report quarantined trips, reasons, and policy notes.' It sharply distinguishes from siblings by focusing on quarantined/excluded rows rather than on-time metrics or late trips. The second sentence reinforces this scope by explicitly stating it explains excluded rows and why.

  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: this tool is for understanding data quality exclusions from OTP metrics. It does not name sibling tools as alternatives, but the contrast is implicit. There is no explicit exclusionary guidance ('use this instead of X'), 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.

• route_otp_summaryA
  4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the transparency burden and does well: it defines 'late' using arrival_delay_min > late_threshold_min, explains the default threshold, states quarantined rows are excluded and listed by id, and notes hidden vehicle overrides are not applied. It lacks return-format details, but an output schema 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 extremely concise and front-loaded: the first sentence gives the core purpose, followed by three tightly-scoped behavioral details. Every line adds unique value with 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?

  The description covers the key behavioral nuances (late threshold, quarantine handling, override exclusion) and an output schema exists, so return values are covered. The main gap is the lack of context around date range parameters, but overall the tool is adequately specified for 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 0%, so the description must compensate. It adds meaning for late_threshold_min (defining the late condition and default) and clarifies route scope, but start_date and end_date are completely unexplained—including format and behavior when null. This is a partial but incomplete compensation.

  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 summarizes on-time performance for one route, with a specific verb and resource. This distinguishes it from siblings like list_late_trips and data_quality_report, which focus on individual trips or broader quality issues.

  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 the tool is for route-level OTP summaries but gives no explicit guidance on when to use it versus list_late_trips or data_quality_report. There are no exclusions or alternative recommendations, only the implied scope of 'one route'.

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