Server Quality Checklist

Tool Scores

• ticker_reportA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It discloses the covered universe (S&P 500 / Nasdaq 100 / major US ETFs), the filtering possibility, the ordering of patterns (newest first), and the paid-key field (hist_win_w20). This goes well beyond a generic 'returns data' statement. It does not mention rate limits or auth, but for a read-only report tool the disclosed behaviors are substantial.

  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 first sentence states the tool's purpose, then Args and Returns sections add necessary detail. Every sentence earns its place, and the null-meaning clarification is high-value. No fluff or repetition of the schema.

  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 read tool with an output schema, the description is nearly complete. It explains the symbol format, the covered universe, null semantics, and result ordering. The only minor gap is that it doesn't describe the pattern objects' fields beyond hist_win_w20, but the output schema likely covers that. Overall, an agent can call this tool correctly with high confidence.

  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 0%, so the description must compensate. It explains the symbol parameter's format ('A US ticker, e.g. "AAPL"'), case-insensitivity, and the universe constraint. It also explains the return fields' semantics (deviation null meaning, patterns ordering). This is strong compensation for a single-parameter tool, though it could add more detail on pattern fields.

  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, specific statement: 'Everything held on one symbol: its current distance from its own ​200-day moving average, and the chart patterns most recently detected on it.' This names the resource (one symbol) and the two concrete outputs, distinguishing it from sibling tools like deviation_ranking or market_stretch. It is not a tautology and gives an agent a precise sense of what the tool returns.

  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 explains the symbol argument format and case-insensitivity, and clarifies the meaning of a null deviation ('not covered', not 'no deviation'). It does not explicitly state when to prefer this tool over siblings, but the scope ('Everything held on one symbol') implies it is the per-symbol detail tool versus ranking/overview siblings. Clear context, but no explicit exclusions or alternatives.

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

• deviation_rankingA
  4.6/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and does so well: it discloses the deviation formula, excludes split-like single-day moves with reasoning, and warns that free accounts always return 2 rows. This is genuinely useful 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 well-organized: summary, formula/exclusion rationale, then argument details. Every sentence adds value, including the split-exclusion explanation and the is_billed check.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  An output schema exists, so return-value details are not needed. The description covers invocation semantics, edge cases, and account-dependent behavior, making it complete enough for an agent to call the tool correctly.

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

  Parameters5/5

  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, and it does. It explains the meaning of direction values, the deviation calculation, and the limit parameter's maximum and free-account behavior. Defaults are left to the schema, which is acceptable.

  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 that the tool ranks symbols by distance from their 200-day moving average and explains both direction modes. It does not explicitly differentiate itself from sibling tools such as market_stretch, so it stops short of a 5.

  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 gives clear usage context: direction='under' is for depressed mean-reversion candidates, direction='over' is for extended names, and the limit/billing caveat is spelled out. It does not mention alternatives or explicit when-not-to-use conditions, but the context is strong.

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

• account_statusA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It explains that the tool validates the key, reports account identity and tier, and clarifies the downstream effects of a free tier. It does not explicitly mention side-effect freedom or failure behavior, but the read-only nature is strongly implied.

  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 purpose appears in the first sentence, followed by a valuable usage note. Every sentence adds information without redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple, has no parameters, and has an output schema. The description provides enough context about what it does and when to use it, making it complete for an agent to select and invoke correctly.

  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 input schema has zero parameters and 100% schema description coverage, so there is nothing for the description to add. The baseline for a no-parameter tool is appropriate here.

  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 validates the configured API key and reports account ownership plus paid-tier status. This distinguishes it from the sibling ranking/report tools, which focus on market data rather than account state.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly tells the agent when to call it: before presenting any list as complete, because free keys truncate rankings to 2 rows and produce null win-rates. This is actionable guidance that prevents misinterpretation of data.

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

• recommended_patternsA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full responsibility. It discloses a critical non-obvious behavior: hist_win_w20 is an aggregate bucket property, not a probability for the specific signal, and that values ≤0.5 imply no edge. It also reveals free-tier behavior (2 rows, null win-rate, is_billed flag). This is far beyond typical transparency and directly prevents misinterpretation.

  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 front-loaded with the core purpose, then provides essential interpretive detail in a separate paragraph, and ends with a clean Args section. It is not overly verbose given the importance of the caveats; each sentence earns its place, though the phrasing could be tightened slightly without losing meaning.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  An output schema exists, so the return format is not needed in the description. The description covers what the tool returns (patterns with win-rates), how to interpret the win-rate, the impact of the limit on free accounts, and the logical check (is_billed). Combined with the output schema, an agent has everything needed to invoke it correctly and interpret results safely.

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

  Parameters5/5

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

  Schema description coverage is 0%, and there is only one parameter (limit). The description adds significant meaning: it defines the effective maximum (100), the free-account default behavior (2 rows), and the side effect of null hist_win_w20. This fully compensates for the lack of 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 description clearly states the resource: K-line chart patterns flagged by the daily scan, with the win-rate of their pattern bucket. It uses a specific subject and modifies it with the key field (hist_win_w20). It is distinct from siblings like market_stretch and deviation_ranking, which focus on other metrics.

  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 gives clear context for when to use the tool (for pattern results) and, more importantly, how to interpret the output responsibly (report the number, not a recommendation). It notes the free-tier limitation indirectly via the `limit` parameter and `is_billed` check. However, it does not explicitly mention alternatives like 'when NOT to use this tool', but the scope is so specific that this is not a major gap.

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

• market_stretchA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full behavioral burden. It reveals the tool's conceptual behavior (breadth vs. index level), the server-side cap of 1000 days, the ordering of returned history, and what each returned component represents. This gives the agent a solid mental model beyond the bare field names.

  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 front-loaded with a one-sentence definition, followed by a short clarifying paragraph and structured Args/Returns sections. Every sentence contributes either conceptual framing, usage guidance, or parameter/return semantics, with no filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a single-parameter read-only metric with an output schema, the description is complete. It covers what the metric means, how to interpret it, the history cap, ordering conventions, parameter advice, and the shape of the return payload. An agent has everything needed to invoke and interpret the result correctly.

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

  Parameters5/5

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

  The schema provides zero description for the 'days' parameter, but the description fully compensates by explaining it in trading sessions, stating that results are newest last, noting the server-side cap, and advising a small value when only the current reading is needed. This adds real semantic value beyond the raw 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 defines the tool with a precise, measurable resource: the share of tracked symbols closing above their 200-day moving average, plus how that reading ranks in its own history. It clearly distinguishes the metric from an index level, so an agent can tell exactly what this tool computes and how it differs from price-level measures.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly states when to use the tool: 'Use it to answer "is the market broadly extended or broadly depressed right now"' and when not to: 'never as a forecast.' It also clarifies that it is a participation/breadth measure rather than an index-level measure, giving the agent enough context to avoid misapplication.

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