Server Quality Checklist

Tool Scores

• get_zone_recordC
  2.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the transparency burden. It reveals some behavioral limits: 'It is not advice, and it does not predict the price,' and it notes the data is a 'reconstructed record since 1971.' However, it does not explicitly state that this is a read-only operation, whether the output is aggregated across all months or per zone, or how missing data is handled.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness2/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single run-on, cryptic sentence that buries the key information mid-phrase. The caveat 'It is not advice' is useful, but the structure makes it hard to parse. This is not concise writing; it is under-specified and awkward.

  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 only one optional parameter and no output schema, so the description must clarify what the returned data represents. It does mention specific metrics (median gold move, inflation adjustment, month count), but the opaque phrasing and lack of any return-format or example leave significant gaps. The relationship to sibling tools is also absent.

  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 fully documents the single 'zone' parameter with an enum and a clear description ('Omit to get every zone'). The tool description adds little parameter-level meaning, but because schema coverage is 100%, the baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose3/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description indicates the tool returns historical gold performance metrics conditioned on a zone ('median gold move 1 and 5 years later, before and after inflation'), so the resource and data scope are somewhat clear. However, it lacks a direct verb like 'get' or 'list', and the opening phrase 'What followed months that read like a given zone' is obtuse. It does not clearly differentiate from siblings like get_current_reading or get_reading_history beyond the word 'zone' in the name.

  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 provides no guidance on when to use this tool versus get_current_reading or get_reading_history. It does not state prerequisites, exclusions, or alternative tools. The only usage hint is implicit in the schema's optional 'zone' parameter, not in the description text.

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

• get_current_readingA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden. It discloses update cadence ('Updated daily after the US market closes'), what the reading contains, and that it is non-advice and non-predictive. It does not describe stale-data behavior or the return envelope, but for a 0-parameter read-only snapshot this is solid coverage.

  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 core content. 'It measures conditions' is mildly redundant since the first sentence already specifies what is measured, but the overall description is efficient and every other sentence earns its place.

  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 0-parameter read tool with no output schema, the description is complete enough: it lists the delivered components (score, zone, measured-part states), update timing, and behavioral limits. It could mention behavior before the daily update, but the basics are all present.

  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?

  There are zero parameters, so the baseline is 4. The description appropriately implies the tool is self-contained (a daily snapshot with no inputs), and nothing about the schema needs elaboration.

  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 names the resource ('Gold Barometer'), the scope ('Today's'), and the exact payload (0-100 score, zone, state of each measured part). The 'Today's' prefix distinguishes it from siblings get_reading_history and get_zone_record, making the purpose unmistakable.

  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 clear usage context: 'Updated daily after the US market closes' tells the agent when data is fresh, and 'not advice... does not predict the price' sets expectation limits. However, it never explicitly names sibling alternatives or states when NOT to use this tool, 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.

• get_reading_historyA
  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 explains the default data scope, the effect of include_reconstructed, the reconstructed date range, and the existence of the long-term archive. It does not cover auth, rate limits, or return shape, but the key behavioral traits are disclosed.

  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 three short sentences with no filler. The main purpose is front-loaded, and every sentence adds meaningful context about ordering, defaults, reconstructed data, or archival scope.

  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-history tool with no output schema and no annotations, the description covers the important decision factors: ordering, default data, reconstructed rows, and the public archive. It could mention limit behavior explicitly, but the schema already describes limit and include_reconstructed well.

  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 description coverage is 100%, so the baseline is 3. The description adds meaningful context beyond the schema by clarifying that daily published readings are the default, that include_reconstructed adds month-end context rows back to 2019, and that the full monthly record is archived separately. This enriches the parameter semantics, especially for include_reconstructed.

  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 identifies the tool as returning past Gold Barometer readings and specifies the ordering ('oldest first'). The phrase 'Past ... readings' distinguishes it from the sibling get_current_reading tool by scope and time horizon, making the tool's purpose immediately apparent.

  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 explicit guidance on the default behavior ('Daily published readings by default') and when to use the include_reconstructed flag for month-end context rows. It also points to the public archive for monthly records back to 1971, signaling when this tool is not the right source.

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