Today's gold buying-conditions score (0-100), its published history, and what followed since 1971.
Scored across 3 tools
The three tools target clearly distinct things: today's snapshot (get_current_reading), a time series of past readings (get_reading_history), and zone-conditioned historical statistics (get_zone_record). While history and zone_record both touch historical data, their purposes (raw series vs. aggregated outcome stats) are unambiguous.
All three follow a get_<modifier>_<noun> pattern (get_current_reading, get_reading_history, get_zone_record), which is predictable and readable. Minor variance in modifier placement (current_reading vs reading_history) is the only deviation.
Three tools is slightly lean but appropriate for a narrow, read-only data service covering snapshot, history, and analytics. Nothing feels redundant or missing at the count level.
For a read-only barometer service, current + history + zone-outcome coverage is essentially complete, with no create/update/delete operations needed. Minor gap: no direct lookup of a single past date, though history arguably subsumes it.
Today's Gold Barometer reading: the 0-100 gold buying-conditions score, its zone, and the state of each measured part. Updated daily after the US market closes. A free email goes out each time the reading moves to a new zone; the result carries the sign-up address. It measures conditions. It is not advice, and it does not predict the price.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose meaningful behavior: the daily refresh cadence tied to the US market close, and the fact that a free email is dispatched on zone changes with the sign-up address carried in the result — a non-obvious side-effect/side-content disclosure. It omits auth requirements or rate limits, which is a minor gap for a parameterless read.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The core purpose and contents are front-loaded in the first sentence, followed by freshness, the email behavior, and disclaimers. It is a touch long and the sentence "the result carries the sign-up address" would benefit from tightening, but every clause carries information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless read with no output schema, the description needs to convey what comes back, and it does at a high level (score, zone, per-part state) plus freshness and caveats. The "state of each measured part" remains vague about the actual return structure, but overall it is complete enough to call correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so per the rubric the baseline is 4. There are no parameter semantics for the description to clarify, and none are cluttering it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource with temporal scope ("Today's Gold Barometer reading") and enumerates exactly what the reading contains: a 0-100 buying-conditions score, its zone, and the state of each measured part. The word "Today's" implicitly separates it from get_reading_history (past readings) and the zone reference distinguishes it from get_zone_record.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides context for use ("Updated daily after the US market closes"), telling the agent when the data is fresh, but gives no explicit when-to-use guidance or routing against the sibling tools get_reading_history and get_zone_record. Usage must be inferred from the phrase "Today's ... reading".
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Past Gold Barometer readings, oldest first. Daily published readings by default; set include_reconstructed to true to add month-end context rows rebuilt back to 2019. The monthly record back to 1971 lives in the public archive.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Newest rows to return. | |
| include_reconstructed | No | Also return month-end reconstructions (rows marked backfilled). |
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.
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.
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.
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.
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.
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.
What followed months that read like a given zone, across the reconstructed record since 1971: median gold move 1 and 5 years later, before and after inflation, with the month count behind each figure. It measures conditions. It is not advice, and it does not predict the price.
| Name | Required | Description | Default |
|---|---|---|---|
| zone | No | A zone name. Omit to get every zone. |
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.
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.
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.
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.
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.
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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_current_readingget_reading_historyget_zone_recordDated exit evidence, depth, tiers and gold cash scenarios. No executable quotes or trade authority.
US dollar index, crisis meter, recession and market-top risk from public-domain data since 1990.
Turkish gold-market digest, derived indicators and analysis search. Keyless, read-only, gated.
Today's Zensei Index: a 0-100 US market risk score, its ten indicators and the latest summary.
Add one secure layer between your agents and this server.
