capabilities

List UK company directors from the Companies House officers register

company_uk_directors

Read-onlyIdempotent

Directors of a UK company from the Companies House officers register — the register of directors, secretaries and LLP members — including corporate and nominee directors, with appointment and resignation dates, nationality, country of residence, occupation, month/year of birth and correspondence address. Use when: Identify who is legally responsible for a UK company - the directors on the Companies House officers register. Not for: You need beneficial owners / persons with significant control — use company.uk.owners. Price: USD 0.005/call (x402), 0.004 (account key).

Input Schema

TableJSON Schema

Name	Required	Description
`role`	No	Which appointments to return. Default `director` — the capability's name is its contract. The register encodes the office in officer_role, so the filter is a substring test on it: `director` matches director, corporate-director, nominee-director and corporate-nominee-director; `secretary` matches secretary, corporate-secretary, nominee-secretary and corporate-nominee-secretary; `llp_member` matches llp-member, llp-designated-member and their corporate- forms; `all` returns every appointment the register lists, including managing officers, general partners, judicial factors and the EEIG/SE organ roles. Filtering is applied after the register read, so read page.has_more rather than items.length.
`limit`	No	Maximum officers to return per page (1-100). Default 5. Eckari reads up to three register pages of 100 entries to fill this after the role and resigned filters are applied; if the limit is still unmet, page.has_more is true and page.next_offset says where to resume.
`offset`	No	Zero-based index into the register's own officer list (not into the filtered result). Pass back page.next_offset from the previous response to page.
`company_number`	Yes	Companies House company number, also called the company registration number (CRN). Accepted shapes are the register's own — 1-8 digits (zero-padded to 8, e.g. 445790 → 00445790), one letter + 7 digits (R0000001), two letters + 6 digits (SC002180, NI000001, OC123456, OE000001), or the registered-society suffix forms (two letters + 5 digits + 1 letter; two letters + 4 digits + 2 letters). Case-insensitive; surrounding whitespace is ignored (which is why maxLength is 10); internal spaces and punctuation are not accepted. Any other value (for example PROBE) is rejected as INVALID_INPUT before payment and before any upstream call.
`include_resigned`	No	Include resigned officers. Default false.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes	Capability output; full JSON Schema at https://api.eckari.com/v1/capabilities/company.uk.directors
`meta`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, yet the description still adds valuable traits: it discloses the per-call price (USD 0.005/call), an operational cost an agent cannot infer from structured metadata, and scopes exactly what the register covers (directors, secretaries, LLP members, corporate and nominee forms). The schema parameter notes further disclose filter-after-read and three-page pagination mechanics. No contradiction with annotations.

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

Conciseness5/5

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

The description is dense but every clause earns its place: core purpose, register scope, included fields, when-to-use, not-for routing, and price. It is front-loaded with the primary purpose before any qualification, and the dash structure keeps the multi-part sentence scannable. There is no filler or repetition of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 params, abstract pagination, substring filters), the division of labor is ideal: the description handles purpose, scope, use-cases, exclusions, and cost, while the schema's exhaustive property descriptions cover parameter mechanics and the output schema covers return structure. Annotations cover safety and data openness. Nothing an agent needs to call this tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema's own property descriptions are exceptionally rich (company_number accepted shapes, role substring-matching semantics, offset meaning). The main description adds no direct parameter guidance beyond mentioning the register scope and corporate/nominee categories, which loosely maps to the role enum. Per the rubric, baseline 3 is correct when the schema does the heavy lifting.

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

Purpose5/5

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

The description states a specific verb and resource — retrieving directors from the Companies House officers register — and enumerates the exact data fields returned (appointment/resignation dates, nationality, occupation, birth month/year, correspondence address). It explicitly differentiates from the most confusable sibling by naming company.uk.owners as the destination for beneficial-owner lookups, so an agent can distinguish it without opening other schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

"Use when: Identify who is legally responsible for a UK company" gives an explicit triggering condition, while "Not for: You need beneficial owners / persons with significant control — use company.uk.owners" supplies an explicit exclusion and the named alternative. This is the ideal when/when-not/alternatives pattern; nothing 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.

All capabilities tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation4/5

Tools are largely distinct, targeting specific entities (UK company, US company, domain, LEI, FX, location, parcel, weather) or sub-aspects (e.g., accounts vs. charges vs. directors). Overlap exists between company.uk.profile and company.uk.status (both contain status info, but the latter is cheaper and focused). Also, company.uk.filings and company.us.filings_latest could be confused if an agent generalizes 'filings' across jurisdictions.

Naming Consistency5/5

All tools follow a consistent pattern: domain_entity_subject (e.g., company_uk_accounts, domain_expiry, weather_us_alerts). Underscores and lower case are used throughout. Verbs are implied by the noun (e.g., 'search' for lookup, 'detect' for identification). No mixed conventions or unpredictable names.

Tool Count4/5

24 tools is on the high side but still reasonable for a general-purpose data server spanning multiple domains (company, domain, entity, fx, location, parcel, weather). Each domain gets a cohesive set, and the documentation justifies each tool. Could be slightly leaner if some niche tools (e.g., domain_expiry vs. registration) were merged, but overall scoping is acceptable.

Completeness4/5

Each domain offers good coverage: UK company tools cover CRUD-like operations (profile, status, search, filings, charges, directors, owners, registered office); similarly for US companies (profile, filings, resolve, latest filings). Weather has forecast, observation, alerts. Parcel only detects carrier (no tracking). Missing features like advanced filtering on company filings or less common domains, but core workflows are covered.

Resources

Need Help?