L50 UK Data API

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds genuinely non-derivable behavior: the external data source (Companies House), per-call cost ($0.05), payment rail (USDC on Base) and protocol (x402). It does not say whether results are paginated or capped in total size, but the cost/auth disclosure is meaningful added context beyond the annotations.

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 zero filler, the substantive data scope front-loaded and the cost/payment caveat trailing. Nothing is wasted, though the absence of any clause addressing date-parameter choice is a content gap rather than a verbosity issue.

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-only, no-output-schema query tool with three parameters, the description covers the domain scope, source and cost, which is the minimum an agent needs. It still leaves open the return shape (grouped per company or flat), pagination, and the days-vs-since semantics, which matter for correct 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 33% schema coverage the description must carry the load, and it only partly does: 'up to 20 UK companies' and 'since a date' map to numbers and since, but the `days` parameter is undocumented in both schema and description, and the likely overlap/precedence between `days` and `since` is left entirely unexplained. An agent has to guess how to choose between the two date parameters.

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-object set (director appointments, resignations, PSC changes) over a specific resource (UK companies) and names the source (Companies House). It is distinguishable from companies_new / companies_overdue, but the near-identical sibling companies_changes_feed is never mentioned, so the agent cannot tell from the description alone which of the two 'changes' tools applies.

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?

Scope constraints ('up to 20 UK companies', 'since a date') imply when the tool fits, but there is no explicit when-to-use/when-not-to-use guidance and no routing to companies_changes_feed or companies_changes_feed_sample. Usage must be inferred from the data scope rather than stated.

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

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

Annotations already declare readOnlyHint and openWorldHint, yet the description still adds genuinely useful behavior: a hard cap of 100 rows, daily refresh from Companies House, and a paid model ($0.10 per call in USDC on Base via x402). It omits what happens on payment failure or rate limits, and does not point at the free sample sibling, which would complete the picture.

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 dense sentences with no filler: scope and freshness first, then filter dimensions, then cost and payment rail. Every clause carries operational weight for an agent deciding whether to spend $0.10.

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-only feed with five optional parameters and no output schema, the definition covers scope, time window, cap, freshness and pricing. The main gap is return shape: with no output schema, the description could say roughly what a row contains beyond the change type.

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 40%, so the description carries partial burden. It maps filters to plain language ('town, postcode, industry and change type') and the 'Up to 100 rows' phrase hints at the max parameter, but it adds no syntax or format detail beyond what the enum and postcode description already supply, and never clarifies locality-versus-town naming.

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-and-resource pair (new director appointments, resignations, PSC changes), a fixed time window ('last 24 hours'), a geography ('UK', 'across all companies') and the filter dimensions. It does not name or differentiate itself from the close siblings companies_changes or companies_changes_feed_sample, so an agent cannot tell from this text alone which of the three to call.

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?

Usage is implied by the 'last 24 hours' framing and the row cap, which suggest a daily-monitoring use case, but there is no explicit when-to-use, when-not-to-use, or reference to the sibling feed_sample or the broader companies_changes tool. The reader must infer routing from the tool name.

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

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

Annotations already cover safety (readOnlyHint) and open-world scope, so the description's job is to add traits: it discloses the hard 3-row cap, the daily refresh cadence, the UK geographic scope, and that the paid feed is the full-data counterpart. It does not describe the returned record shape, which matters since there is no output 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?

Two short sentences, no filler, and the key constraint (free, max 3 rows) is front-loaded before the filter-parity note. 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 simple 4-optional-parameter read tool with no output schema, the description covers source, scope, row cap, and filter behavior. The remaining gap is the shape of the returned rows, which neither the description nor an output schema supplies.

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 50% — types and postcode are documented in-schema, while industry (enum only) and locality carry no text. The description adds only the pointer that filters match companies_changes_feed, which hints at filter parity but gives no semantics for the two undocumented parameters.

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 and resource — returns up to 3 rows from the daily UK director and owner changes feed — plus the free-tier cap and the exact sibling whose filters it mirrors. An agent can distinguish it from companies_changes_feed and companies_changes without opening either schema.

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?

"Try before you pay" plus "same filters as companies_changes_feed" makes the evaluation use case and the paid alternative clear. It stops short of an explicit instruction such as "switch to companies_changes_feed when you need complete results," leaving that inference to the agent.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely non-obvious behavior: a $0.10 per-call charge settled in USDC on Base via x402, plus a hard 10-result cap — an agent needs both before calling. It stops short of describing response shape or what happens when no filters are supplied.

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 sentences, with the resource and scope front-loaded and the cost/payment constraint appended as a distinct operational sentence. Every clause carries information; nothing is padding.

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?

Without an output schema, the description carries the return-value burden and partially does so by naming director, website check and email details. However, for a five-parameter tool with zero schema documentation, it leaves defaults, the recency window semantics, and unfiltered behavior unexplained.

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 0%, so all five parameters fall to the description. It maps town/postcode/industry to locality/postcode/industry but says nothing about 'max' (its default or cap semantics beyond 'up to 10') or 'days' (the recency window and its 1–30 range), leaving two parameters with no meaning anywhere.

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 and scope: newly registered UK companies from Companies House, capped at 10, filterable by town, postcode or industry. The 'newly registered' framing implicitly separates it from siblings like companies_changes and companies_overdue, but no sibling is named explicitly.

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 statement of when to use this versus companies_changes or companies_changes_feed, and no prerequisites. The only contextual guidance is operational (cost and payment rail), which is useful but not usage guidance.

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

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses a hard result cap of 10 and, unusually, the commercial model — $0.20 per call settled in USDC on Base via x402 — which materially affects whether an agent should invoke it. It does not cover rate limits, pagination, or what happens with zero results.

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 zero filler, front-loading the result shape and follow-up usage before the cost caveat. Every clause carries information an agent needs.

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-only, filter-driven lead-gen tool with no output schema, the description usefully states the returned fields and the result ceiling. However, it never explains filter interactions or defaults (e.g. what mode/locality do when omitted), leaving gaps an agent must guess at before calling.

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 0% schema description coverage, the description has to carry parameter meaning and only partly does: 'Up to 10' clarifies the max cap and 'overdue (or soon-due)' hints at the mode enum. Industry, locality, and dueWithinDays — including their defaults — are left entirely to the bare 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?

The description names a concrete resource — UK companies with overdue or soon-due Companies House accounts — and the payload it carries (director and email details), which separates it from sibling feeds like companies_new or companies_changes_feed. It omits an explicit verb, but the retrieval intent is unambiguous.

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?

'Leads for accountants' implies the intended audience and use case, but there is no explicit when-to-use framing, no named alternatives among the sibling company tools, and no statement about when this is inappropriate. Usage is inferred rather than stated.

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

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

Annotations already cover safety (readOnlyHint) and scope (openWorldHint), and the description adds genuinely new behavioral context: this is a paid call at $0.02, settled in USDC on Base via x402, and the data is 'live' rather than cached. It does not mention rate limits, latency or failure modes, which keeps it short of 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?

A single dense sentence with zero filler: the capability, the site scope, the returned metrics and the pricing model all appear in order of importance. Nothing is repeated from the schema or annotations.

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 correctly compensates by enumerating return fields, and it discloses the payment requirement that an agent must handle before calling. The remaining gap is default/fallback behavior for the optional marketplace parameter.

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 only 33% (only cost is documented), so the description has to carry weight. It partially does: 'for one keyword' clarifies keyword as a single search term, 'on 8 eBay sites' frames the marketplace enum, and 'optional profit from your cost' explains the cost parameter. It never states the default marketplace when the parameter is omitted, leaving a real gap.

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?

Names the resource (live eBay market data for one keyword across 8 eBay sites) and enumerates the concrete outputs: price range with postage, seller concentration, China share, cheapest listings and optional profit. That is far more specific than a restatement of the name, though the verb is implicit (fetch/analyze) 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 mention of 'optional profit from your cost' implicitly tells the agent when to supply cost, and 'on 8 eBay sites' implies the marketplace selector. However there is no explicit when-to-use or when-not-to-use guidance, and no statement about what happens if marketplace is omitted.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful non-schema context: a per-call cost of $0.05 paid in USDC on Base via x402, plus the explicit statement that no address-level records are returned.

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, front-loaded with the core purpose, then the geographic limitation, then the cost. Every sentence adds information; the only nit is that the cost caveat would read better after the scope caveat rather than as a trailing sentence.

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?

There is no output schema, but the description says enough about the shape of the result (share of ratings A-G per postcode district) for an agent to interpret the return value. Still, for a five-parameter tool with only 20% schema coverage, the missing explanation of the time window and the minimum-certificate filter leaves gaps that matter for correct 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?

Schema description coverage is only 20%, so the description must carry weight: it maps to 'one council' (required), 'per postcode district' (one groupBy option), and 'homes or commercial buildings' (buildingType domestic/non_domestic). However, it never explains the 'months' lookback or 'minCertificates' threshold, nor the constituency/council groupBy options, leaving real gaps.

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 uses a concrete verb+resource: EPC statistics for one council in England or Wales, broken down by rating band A-G and geography. The scope qualifier 'Area-level only, no addresses' helps distinguish it from a sibling like property_area, but no sibling is named explicitly.

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?

Usage is implied by the 'area-level only, no addresses' constraint, which signals when not to use it, and by naming the geographic unit as a council. It never states alternatives, prerequisites, or when to pick a different geographic breakdown tool.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external-data status are covered. The description goes beyond them with material operational context: a metered cost of $0.05 per call, settled in USDC on Base via x402, which an agent must know before invoking a paid endpoint. It stops short of disclosing latency, rate limits, or upstream data freshness.

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 sentences, front-loaded with the resource and its contents, followed by the scope caveat and the pricing constraint. No filler or repetition of the schema. Slightly dense in the first sentence, but every clause carries distinct 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?

There is no output schema, so the description correctly takes on the burden of describing what comes back: sold prices segmented by property type with change versus the previous period, EPC ratings, and crime figures. Combined with the cost disclosure and area-only boundary, an agent has enough to decide and invoke correctly; response shape and data recency remain unspecified but are secondary.

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 100%, with every parameter including defaults, ranges and the district regex documented inline, so the baseline is 3. The description adds only framing value — that district scope is a single area and that months implies a same-length prior-period comparison — and does not clarify the crime/energy toggles or the effect of months on cost or payload size.

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-and-resource combination: a UK property report for one postcode district, and enumerates the three data feeds it aggregates (Land Registry sold prices by property type with period-on-period change, EPC ratings, police.uk crime). The scope qualifier 'Area-level, no addresses' plus 'England or Wales' makes it distinguishable from the sibling epc_areas tool, which covers only the energy component.

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?

Usage is implied rather than prescribed: the agent can infer this is the right tool for aggregated area-level property research on a single district, and that full-address questions are out of scope. However, it never names an alternative or states when to prefer epc_areas (for EPC-only needs) or when a district-level rollup is insufficient, so the routing versus siblings is left to inference.

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

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

Adds substantial context beyond the readOnly/openWorld annotations: a per-call cost of $0.05 paid in USDC on Base via x402, daily refresh cadence, and hard caps of 100 notices and 30 days back. That payment requirement is critical information an agent needs before calling. It stops short of describing pagination or result-shape behavior, so not 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 dense sentences with no filler: resource and sources first, filter axes second, then the operational constraints (caps, freshness, price). Every clause carries information an agent needs.

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 10-parameter, all-optional tool with no output schema, the description covers the resource, filters, limits, freshness and cost. The remaining gap is what a returned notice looks like in tenders mode versus awards mode, which matters since there is no output schema to fall back on.

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 90%, so the schema already documents nearly every parameter including enums and examples. The description only restates the filter axes generically ('keyword, CPV code, region and value') without adding syntax or interplay rules (e.g. how keywords and exclude combine). Baseline 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?

States a specific verb+resource: UK public sector tenders open for bids and contract awards, and names both upstream sources (Find a Tender and Contracts Finder). It also scopes the data returned for awards (winning suppliers with Companies House number, email, phone), so an agent knows exactly what it is getting.

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?

Gives clear usage context: mode selection between open bids and awards, and the filter axes (keyword, CPV, region, value). There are no competing sibling tools to route away from, so the absence of explicit exclusions costs little, but it never states when this tool is the wrong choice (e.g. non-UK procurement).

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

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds substantial behavior beyond them: the pricing model, the payment rail (USDC on Base via x402), and the error behavior (captionless videos are refused and not charged). It stops short of rate limits, max video length, or partial-failure handling, keeping it below the top mark.

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 sentences with no waste: the first front-loads what the tool returns, the second carries the commercial and failure behavior. Every clause earns its place and the pricing detail is appended rather than buried.

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?

There is no output schema, so the description carries the burden of describing return values, and it does so (clean text plus title, channel, language, optional segments). Payment and failure semantics are covered. Minor gaps remain around truncation, pagination, or behavior for very long videos, which matter for an agent calling a paid endpoint.

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 all three parameters are already documented with defaults and formats. The description corroborates meaning by mentioning 'timestamped segments' and language metadata, but adds no syntax or format detail the schema does not already carry. Baseline 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?

States a specific resource (the transcript of one YouTube video) with scope qualifiers (Short or livestream, clean text) and lists the payload contents (title, channel, language, optional timestamped segments). An agent immediately knows what this returns, and none of the sibling tools overlap with this function.

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?

Provides cost ($0.01/call) and a failure condition (videos without captions are refused at no charge), which lets an agent judge whether to call it. However, there is no explicit when-to-use or when-not-to-use guidance, and no named alternatives (the siblings are unrelated domains, so no routing guidance is offered).

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