UK Data: UK Companies House

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

With no annotations, the description carries the full disclosure burden. It usefully states the source (Companies House advanced search) and the cost ('2 credits'), which is real context an agent cannot get elsewhere. It omits read-only confirmation, result shape, ordering, pagination/limit behavior, and whether exceeding limits truncates or errors.

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 compact fragments, front-loaded with the verb and resource, then filters, then API source, then use case and cost. Nothing is padded, though the sentence-fragment style ('New-business lead lists.') is slightly telegraphic.

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 7-parameter, no-annotation, no-output-schema search tool, the description covers what can be filtered and what it costs but not what comes back (fields, count, ordering) or how the limit interacts with total matches. An agent could invoke it, but not confidently predict or explain the output.

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; parameters are already self-documented including the '["active"]' default for status and the 1-100 limit. The description adds meaning only at the aggregate level by naming which filters exist, without clarifying interactions such as whether filters are ANDed or how SIC codes are matched.

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 gives a specific verb ('Find') plus the resource ('companies') and enumerates the filter dimensions (incorporation date range, SIC codes, status, location, name fragment), which lets an agent distinguish it from name-lookup siblings like company_search and record-detail siblings like company_profile/company_filings. It falls short of 5 only because no sibling is named directly.

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?

'New-business lead lists' implies the intended use case, and the filter list hints at what queries belong here. There is no explicit when-not guidance, no mention of when to prefer company_search or company_profile instead, and no prerequisites such as API key or coverage limits.

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?

With no annotations supplied, the description carries the full burden. It does add genuinely useful behavior beyond the schema by disclosing a cost of 1 credit and implying a read-only historical lookup, but it says nothing about ordering, pagination, or what happens with an invalid or unknown company number.

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 front-loaded sentence naming the resource and its contents, followed by a bracketed cost note. Nothing is wasted, though the cost note could be folded more cleanly and the parenthetical list is dense.

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 and no annotations, so the description must cover everything. It does tell the agent what categories of filings come back, but omits result shape, ordering, pagination behavior, and error cases for a tool whose main complexity is the breadth of returned filing data.

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 are already documented in the schema. The description reinforces that companyNumber is the key input but adds no format guidance (e.g. with or without leading zeros) and never mentions the limit parameter, so it does not exceed the schema baseline.

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 (filing history) keyed on a company number, and enumerates the record types returned (accounts, confirmation statements, officer changes, charges). This distinguishes it reasonably well from siblings like company_officers or company_profile, though it never explicitly says it is the Companies House filing feed, so the agent must infer the jurisdiction.

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 only implied: the enumerated record types suggest 'use this when you want the historical filing record rather than current officers or profile data'. There is no explicit when-to-use statement, no mention of alternatives such as company_officers or company_profile, and no prerequisites or failure conditions given.

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?

No annotations are supplied, so the description carries the full load. It does disclose two genuinely useful behavioral facts an agent cannot get from structured fields: the result content includes appointment and resignation dates, and the call costs 1 credit. It says nothing about pagination, volume of officers returned, or whether historical/resigned officers are included by default.

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 sentence plus a parenthetical cost note, front-loaded with the resource and scoped by the input. Nothing is redundant and the credit cost is placed where it is easy to scan before invocation.

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 two-parameter read lookup with no output schema and no annotations, the description covers purpose, result content and cost, which is most of what an agent needs. The remaining gap is the semantics of the default active-only filtering, which neither the description nor the schema description text resolves.

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 and the schema already documents both parameters. The mention of "resignation dates" loosely implies the activeOnly filter's meaning, but the description never explains what activeOnly=false actually changes in the response.

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?

"Directors and secretaries for a company number" states a specific resource and the key input, and the phrase naturally separates it from sibling lookups like company_pscs (persons with significant control) or company_filings. It stops short of naming those siblings explicitly, so an agent must infer the boundary rather than being told it.

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 when-to-use or when-not-to-use guidance and no mention of alternatives (company_profile, company_pscs, company_filings) that return adjacent company data. The only contextual hint is the implicit prerequisite that a company number is needed, presumably from company_search.

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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses a cost of 1 credit and enumerates the categories of returned data, including overdue flags, charges, and insolvency flags. However, it does not state error behavior, authentication/rate-limit constraints, or whether missing data is returned as null versus omitted.

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 dense sentence with the resource and scope front-loaded, followed by the key returned fields and cost. Every element is useful for selection and invocation, with no redundant wording.

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 one-parameter read lookup with no output schema, the description is largely complete: it defines the resource, lists major returned categories, and discloses the credit cost. It remains slightly incomplete because it omits company-number format expectations and explicit routing guidance among related company tools.

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 single parameter is already documented as a required company number. The description only restates that lookup is by company number and adds no format guidance such as expected length, prefix, or examples. Baseline 3 is appropriate because the schema does the substantive work.

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 the specific resource and scope: a full Companies House profile keyed by company number. It enumerates returned data such as status, SIC codes, registered office, accounts dates, charges, and insolvency flags, making the tool's purpose clear. It does not explicitly contrast itself with siblings like company_search, company_filings, or company_officers, so it falls 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.

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

There is no explicit when-to-use guidance, no prerequisites, and no named alternatives. An agent can infer that this is for retrieving a company's full profile, but the many related sibling tools are not addressed. It does not mention using company_search first if the company number is unknown.

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?

No annotations exist, so the description carries the full burden. It does disclose the meaningful behavioral trait of cost ('1 credit') and implies a read-only lookup by asking for a company number, but it says nothing about empty results, invalid-number errors, or whether the data is cached or live.

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 tight sentence with the resource front-loaded and the cost tucked in parentheses. Nothing is wasted and nothing important is 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?

For a one-parameter lookup with no output schema, the definition is workable but thin: it never indicates what a PSC record contains (names, addresses, nature of control) or how to interpret an empty response. An agent can invoke it, but cannot predict its payload.

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% for the single required parameter, so the baseline is 3. The phrase 'for a company number' maps the input to Companies House-style company numbers, but adds no format, prefix, or validation detail beyond that.

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 the resource precisely and expands the acronym ('Persons with significant control (beneficial owners)'), which makes the tool's data unambiguous. It lacks an explicit verb and doesn't name the sibling it differs from (e.g., company_officers), so it falls short of 5.

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 when-to-use or when-not-to-use guidance and no mention of siblings such as company_officers, company_profile, or company_filings that an agent must choose between. The only routing signal is implicit in the resource 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?

With no annotations, the description must carry behavioral disclosure, and it does contribute two real facts: the return shape (number, status, type, incorporation date, address) and the cost of 1 credit. It omits pagination behavior, default limit, and any auth or rate-limit context, so the behavioral picture is only partially filled in.

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 action and immediately followed by the return fields and cost. No filler, no redundant restatement of the tool name.

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 two-parameter search tool with no output schema and no annotations, the description adequately covers what it does, what it returns, and what it costs. Minor gaps remain around result limits and how to act on a match, but nothing essential to calling it correctly is missing.

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 schema already documents both parameters (query as required string, limit as number 1-100). The description only adds the semantic that the query is a company name; it says nothing about how limit interacts with results or what happens at the cap.

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 ("Search Companies House by name") and names the lookup key, which distinguishes it from profile-style siblings like company_profile and company_filings. It stops short of explicitly naming those siblings, so the differentiation is inferred 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?

"by name" implies you need a company name rather than a company number, which is useful routing context against company_profile. However, there is no explicit when-to-use/when-not guidance, no mention of what to do after finding a match, and no named alternatives among the many company_* siblings.

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