Semiconductor fabs, published forecasts and their restatements, each row naming its publisher.
Scored across 9 tools
Each tool targets a distinct resource or question: searching fabs vs profiling one fab, listing figure subjects vs tracing one figure's history, listing sources, defining node bands, showing recent restatements, and exposing record gaps/overview. Overlaps are minor and descriptions clearly separate them.
All names use snake_case and are readable, but the set mixes verb-first names like find_fabs, list_figures, and list_sources with noun-first names like fab_profile, figure_history, record_gaps, and record_overview. The pattern is mixed rather than a consistent verb_noun convention.
Nine tools is well-scoped for a read-only data record: discovery, search, profile, history, sources, definitions, recent changes, gaps, and overview each earn their place. No obvious redundant or trivial tools.
The surface covers the apparent read-only domain well: orientation, fab search and profiling, figure subject listing and history, source listing, node-band definitions, recent restatements, and explicit gap reporting. No critical missing operation stands out for this record's stated purpose.
One fab site in full, including the note that says what this record does not know about it, and every capacity statement whose sentence covers it.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new information about composition — that the response bundles the record's gaps note and all capacity statements scoped to it — but says nothing about missing-id behavior or response shape.
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?
One compact sentence with the scope front-loaded ('One fab site in full'), which is good. But the qualifying clauses are wordy and convoluted, costing clarity without adding proportional value.
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?
With no output schema, the description does sketch the return contents (record, gaps note, capacity statements), which is the right instinct. It still leaves the id format and not-found behavior unspecified for a single-parameter lookup tool.
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?
There is one required parameter, 'id', with 0% schema description coverage, so the description carries the burden and does not meet it: it never states that the id identifies a fab, nor what form the identifier takes. The single implicit mapping to 'one fab site' is the only compensation.
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?
It conveys that the tool returns one fab site's full record, plus its gaps note and covering capacity statements. But the phrasing ('the note that says what this record does not know about it', 'every capacity statement whose sentence covers it') is opaque domain jargon, and the description never names the sibling it differs from (find_fabs, record_overview).
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?
No explicit when-to-use guidance and no exclusions. An agent must infer that this is the detail view for a single fab versus find_fabs for discovery or record_overview for a summary; the description never makes that routing explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The revision history of one published figure: every vintage, what the publisher said in their own words, the date they issued it, and the link. Includes the restatements as pairs of published values. Call this when a number is quoted and you want to know what the same publisher said before. It states no reason for any change.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | ||
| subject_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds useful behavioral context by describing the returned history, restatement pairs, and the important limitation that it states no reason for any change.
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 front-loaded with the core purpose, then adds return content, usage guidance, and a limitation in four efficient sentences. There is no redundant restatement of the name or title.
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?
It covers the return content well enough despite having no output schema, and annotations cover the safety profile. However, for a two-parameter tool with 0% schema description coverage, the missing explanation of subject_id and target leaves a meaningful gap.
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 0%, and the description does not explain either parameter. It only implies that subject_id identifies the figure via 'one published figure,' while the optional target parameter is left completely unexplained.
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 states a specific verb and resource: the revision history of one published figure. It scopes the result to every vintage, publisher wording, issue date, link, and restatement pairs, which clearly distinguishes it from generic figure listing or recent-change tools.
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 gives an explicit usage trigger: call this when a number is quoted and you want to know what the same publisher said before. It does not name when not to use it or point to sibling alternatives such as list_figures or recent_changes, so it falls short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the fab sites in the record by country, operator, kind, status, wafer size or process node. Every row names the publisher it came from; rows with no publisher are not returned.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| node | No | ||
| type | No | ||
| limit | No | Rows to return, 1 to 200. Default 50. The envelope always reports the true total separately. | |
| offset | No | Rows to skip, for paging. | |
| status | No | Exact match, case-insensitive. Values: operating, construction, announced, paused, cancelled, closed, closing. closing = production continues while a phase-out has been publicly announced. | |
| country | No | ||
| operator | No | ||
| wafer_mm | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-open-world), so credit goes to genuinely new information: the provenance rule that every returned row names its publisher and that unpublished rows are silently excluded. That is a non-obvious result-set constraint an agent could otherwise misread as 'no fabs exist'. It stops short of describing ordering, paging behavior, or result shape.
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?
Two tight sentences: the searchable dimensions come first, the provenance caveat second. No filler, no restatement of the title, and both sentences carry operational weight.
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 9-parameter, zero-required search tool with no output schema and partial schema coverage, the definition covers the filtering semantics and one important result-set caveat. The unexplained 'q' free-text parameter and the absent note on ordering/paging are the remaining omissions, but neither blocks a correct first call.
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?
With only 33% schema coverage, the description must compensate, and it largely does by enumerating the filter dimensions (country, operator, kind, status, wafer size, process node) that map to country, operator, type, status, wafer_mm and node. The gap is the free-text 'q' parameter, which appears nowhere in the description, and the 'kind' wording that does not literally match the schema's 'type' key.
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?
States a specific verb ('Search') and resource ('fab sites in the record') and enumerates the filter dimensions, which makes it clearly the discovery/screening tool as opposed to the detail-oriented sibling fab_profile. It does not name any sibling explicitly, so the differentiation is implicit rather than stated.
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 verb 'search' plus the filter list implies the use case (narrow down fabs by attribute), but there is no explicit when-to-use, when-not, or pointer to fab_profile / record_gaps for other tasks. Nothing tells the agent whether to search first and then profile, or what to do if no rows come back.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every published forecast subject in the record and each year it has been forecast for, with how many vintages exist. Use it to find a subject_id for figure_history.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Rows to return, 1 to 200. Default 50. The envelope always reports the true total separately. | |
| offset | No | Rows to skip, for paging. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that the result is an exhaustive enumeration of all published subjects (no filtering), which is genuinely useful context. It omits any note on scale or result size, though the schema's limit notes the envelope reports the true total.
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?
Two compact clauses: what the rows contain first, then how to use the result. Zero filler and no restatement of the title.
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?
With no output schema, the description carries the burden of describing row contents and does so concretely (subject, years forecast, vintage count). Combined with 100% schema coverage on paging, an agent has enough to call it correctly. Only the expected result volume is unaddressed.
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 both parameters (limit, offset) are fully documented including the default and the true-total envelope behavior. The description says nothing about paging or params, so the baseline 3 applies.
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 the resource (published forecast subjects) and the exact payload per row: each year forecast and the count of vintages. That is more specific than 'list figures' and lets an agent predict the shape of the listing. It differentiates only against figure_history, not against other listing siblings like list_sources or find_fabs.
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 gives an explicit use case with a named follow-up: 'Use it to find a subject_id for figure_history', which is a clear cue for the resolve-then-query workflow. It stops short of exclusions — it doesn't say when to use find_fabs or fab_profile instead when the agent already knows what it wants.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every publisher this record collects, across BOTH mechanisms: their feed, or their own sitemap. A publisher absent from one may be present in the other.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| limit | No | Rows to return, 1 to 200. Default 50. The envelope always reports the true total separately. | |
| bucket | No | ||
| offset | No | Rows to skip, for paging. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: results are a union across two collection mechanisms, so an agent must not assume a publisher missing from one channel is missing entirely. It still says nothing about ordering, pagination behavior, or what a source entry contains.
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?
Two short sentences, front-loaded with the scope and followed by the one nuance that changes interpretation. No filler. It is arguably under-specified rather than verbose, and 'this record' is an unanchored reference.
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 4-parameter list tool with no output schema and no annotations gap on safety, the description covers the semantic core but leaves the two undocumented parameters and the shape of a returned 'source' unexplained. An agent can call it without arguments, but cannot use q or bucket confidently.
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?
Only limit and offset are documented in the schema (50% coverage); q and bucket have no description anywhere. The description does not mention any parameter, so an agent gets no hint about what q searches over or what values bucket accepts — exactly where compensation was needed.
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?
States a specific resource (publishers/sources) and its scope: everything the record collects via feed OR sitemap. That is far more informative than the title 'List sources'. However, it never uses an explicit verb like 'list'/'returns' and refers to 'this record' even though the schema has no record parameter, leaving the implicit scoping slightly fuzzy.
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 second sentence implies when the union view matters ('A publisher absent from one may be present in the other'), so the tool's raison d'être is inferable. But there is no explicit when-to-use, no mention of when a filtered lookup would be better, and no guidance tying it to the sibling tools (fab_profile, find_fabs, etc.).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How named publishers have defined process-node bands such as "advanced", each as a dated statement with its wafer basis. This record defines no bands of its own.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare the tool as read-only, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful scope context by noting that this record defines no bands of its own and that entries are dated statements with a wafer basis, but it does not describe output format or record structure.
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 two sentences and front-loads the core purpose before adding the scope disclaimer. Every sentence contributes directly to understanding what the record contains and does not contain.
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?
With no parameters, no output schema, and annotations covering safety and idempotency, the description supplies enough context about the content of the record. It could be slightly more complete by clarifying whether the result is a list of publisher statements or a single aggregate record.
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 has zero parameters, so there is no parameter semantics to explain. Per the baseline for zero-parameter tools, a 4 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 clearly states that the tool exposes how named publishers have defined process-node bands, including dated statements and wafer basis. This is a specific resource description, though it does not explicitly distinguish itself from the sibling tools such as fab_profile or figure_history.
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?
There is no explicit guidance on when to use this tool versus alternatives. The implied use case is looking up publisher-defined node-band terminology, but the description does not state any conditions, exclusions, or sibling routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Figures that publishers restated recently, each an old value and a new value with both links. Says what changed and never what it means.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| limit | No | Rows to return, 1 to 200. Default 50. The envelope always reports the true total separately. | |
| offset | No | Rows to skip, for paging. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world). The description adds real behavioral context beyond that: the payload is a paired old/new value with links, and critically it 'says what changed and never what it means' — warning the agent not to expect interpretation. It does not clarify the default time window or paging behavior, which keeps it below a 5.
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?
Two tight sentences with no filler, and the payload shape is front-loaded ahead of the interpretive caveat. Nothing to cut.
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?
With no output schema, the description carries the burden of describing return values, which it partly does (paired old/new values with both links). The gap is the days parameter: an agent cannot tell what window 'recently' covers or what happens if days is omitted, which matters for a change-feed tool.
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 coverage is 67%, with limit (1–200, default 50, envelope reports true total) and offset well documented in the schema itself. The description's 'recently' vaguely gestures at the undocumented days parameter but never states its default or unit, so it adds little beyond the schema.
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?
States concretely what the tool returns: figures publishers restated, each paired as an old value and a new value with both links. That is specific enough to distinguish it from list_figures or record_overview, though it never names the closest sibling (figure_history) to sharpen the contrast.
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?
There is no explicit when-to-use statement, no prerequisites, and no mention of alternatives such as figure_history. The agent must infer from 'restated recently' that this is the change-feed view, and must guess how it differs from history lookups.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What this record is missing and why each one is open. Call it before concluding a figure exists. Statuses distinguish "nobody publishes this" from "the source costs money" from "we have the URLs and have not done the work".
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| limit | No | Rows to return, 1 to 200. Default 50. The envelope always reports the true total separately. | |
| offset | No | Rows to skip, for paging. | |
| status | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety bar is covered. The description adds real value beyond them: it explains the status taxonomy that separates never-published gaps from paywalled ones from unworked ones. It does not describe the response envelope or ordering, though pagination is handled by the schema.
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?
Three short sentences with no filler; the purpose and the pre-conclusion trigger are front-loaded. The status taxonomy is compressed into a single parallel clause that reads well. Slightly cryptic phrasing in sentence two costs a point but nothing is wasted.
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?
A four-parameter, no-output-schema read tool needs its description to carry the return shape and key parameter meanings. The gap/status model is well conveyed, but the ambiguity of `q` and the absence of any statement about the result envelope (beyond what `limit` describes) leave an agent guessing before invocation.
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?
At 50% schema coverage the description must compensate. It does add genuine meaning to the bare `status: string` parameter by explaining what the status categories represent. However, `q` is entirely unaddressed — an agent cannot tell whether it is a record identifier or a free-text search — and no actual status values are enumerated.
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?
"What this record is missing and why each one is open" states a specific resource (gaps open on a record) and the payload (reason per gap). It is clearly distinct from siblings like record_overview or list_sources. It never states an explicit verb (list/return) or which record, but the resource is unmistakable.
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?
"Call it before concluding a figure exists" is a concrete, actionable trigger with a stated failure mode it prevents. It does not name sibling alternatives or say when not to call it, but the use condition is explicit rather than inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Start here. What this record holds, what it refuses to do, and the latest changes. Read it before assuming what is available.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond that: it reveals that the overview covers what the record 'refuses to do' and the latest changes, which tells the agent it will learn about limitations and recent state. It does not describe output formatting, but that is a minor gap given the annotation coverage.
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?
Three short sentences with no wasted words. The most important instruction, "Start here," is front-loaded, and each sentence adds a distinct piece of guidance.
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 zero-parameter, read-only overview tool with no output schema, the description adequately explains what the tool surfaces: holdings, limitations, and recent changes. It could be more complete by clarifying what 'record' means or hinting at the return structure, but it covers the essential orientation role.
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 there is no parameter semantics for the description to clarify. The baseline for a parameterless tool is 4.
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 gives an overview of a record: what it holds, its limitations, and recent changes. However, it never specifies what kind of 'record' this refers to or what operation is performed, leaving the purpose only partially clear. It also does not differentiate itself from siblings like record_gaps or recent_changes.
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?
"Start here" and "Read it before assuming what is available" give clear guidance on when to invoke this tool: as an initial orientation step. It does not name specific alternatives or exclusions, but the sequencing advice is explicit enough to guide an agent.
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.
find_fabs1 field changedInput schema / properties / status / descriptionAdded value: +"Exact match, case-insensitive. Values: operating, construction, announced, paused, cancelled, closed, closing. closing = production continues while a phase-out has been publicly announced."fab_profilefigure_historyfind_fabslist_figureslist_sourcesnode_bandsrecent_changesrecord_gapsrecord_overviewDated, sourced semiconductor data: chip costs, HBM/wafer pricing, fab capacity, policy, forecasts.
How often financial news sources were right vs. chance, with 95 % intervals. Read-only, CC BY 4.0.
Lead times, prices, tariffs and grid interconnection terms for factory and datacenter equipment.
Forecast track records: forecasts vs actuals, earnings beats, prediction markets, archived news.
Add one secure layer between your agents and this server.
