UK Data: UK due diligence

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

Annotations already cover read-only, idempotent, non-destructive, open-world behavior, so the description's added value is the jurisdictional limit (England and Wales only), the temporal depth of the data (five years of income history), and an explicit 2-credit cost that lets an agent reason about budget. It does not disclose behavior for an unknown or non-existent charity number, but the operational context it does add is genuinely useful.

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, front-loaded with the identity of the resource and scope, then a colon-delimited inventory of return contents and cost. Zero filler; every clause carries information an agent would otherwise have to infer.

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 the response, and it does so by enumerating the profile sections an agent will receive. For a rich, multi-section profile this is close to sufficient; the remaining gaps are failure behavior for invalid/unknown charity numbers and routing against the sibling charity 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 coverage is 100% for the single parameter and already gives the type, the 'required' note and an example ('202918'); the description only adds that it is a charity number scoped to England and Wales. That is marginal added meaning, so the baseline of 3 for a fully documented schema is correct.

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?

Specific verb+resource with explicit scope: 'Full profile of a charity in England and Wales by charity number', followed by an enumerated payload (status, activities, address/contacts, income/spending, staff, volunteers, trustees, five-year income history). An agent immediately knows this is the deep-detail endpoint versus a lighter lookup. It does not name or distinguish itself from sibling charity_lookup or charity_search, so it stops 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?

Usage is only implied: the word 'Full' and the '(cost: 2 credits)' tag hint that this is the expensive, detailed option and that cheaper siblings exist, but no when-to-use/when-not-to-use rule or explicit alternative is stated. An agent must infer that charity_search is for discovery and this is for a known charity number.

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, idempotentHint and non-destructive behavior, so the bar is lower. The description still adds real value beyond them: the England-and-Wales jurisdiction and an explicit per-call cost of 1 credit, which matters for planning repeated searches. It does not explain how closed/removed charities affect results, leaving that to 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?

Two sentences, both front-loaded with the core action and the decision-driving use case. The cost note is compact and placed at the end where it does not bury the main purpose. No filler 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 three-parameter read tool with no output schema, the description covers jurisdiction, purpose, returned fields and cost. The one material omission is sibling routing among charity_search, charity_lookup and charity_profile, which an agent would need to choose correctly.

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

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

Schema description coverage is 100%, so name, limit and includeRemoved are already documented in structured form, making 3 the baseline. The description confirms name-based lookup but adds no meaning about match semantics (exact vs partial), pagination, or what includeRemoved 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?

States a specific verb and resource (find a registered charity in England and Wales by name) plus the fields returned (charity number, status, registration date). It does not differentiate itself from the sibling tools charity_lookup and charity_profile, so an agent cannot tell from the description alone which one to pick.

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 a concrete use case — verifying a charity is real before donating, partnering or paying it — which implies when to reach for it. It offers no when-not conditions and never names charity_lookup or charity_profile as alternatives for looking up by number or fetching deeper details.

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 readOnly/idempotent/openWorld annotations, the description discloses the failure mode (PDF-only filers cause the tool to say so and link the filing), conditional field availability ('where published'), a prior-year comparison column, and a cost of 3 credits. Those are exactly the operational facts annotations cannot express, especially the coverage cliff for large companies.

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 sentences, front-loaded with what is returned, then coverage limits, then use cases and cost. Every clause carries information — the field list, the PDF limitation, the credit cost — with no filler or 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?

With no output schema, the description compensates by listing the returned figures and noting the prior-year comparison, plus the partial-result behavior for PDF filers. For a one-parameter read tool with safety annotations already supplied, nothing material an agent needs in order to call 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% for the single companyNumber parameter, including an example format, so the schema already carries the parameter burden. The description adds nothing about the identifier (no note on format, no cross-reference to company_search for resolving names to numbers), which is the baseline-3 outcome for a fully documented 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 specific verb-level action (extract headline figures from the latest filed accounts at Companies House) and enumerates the exact resource fields returned: net assets, cash, debtors, creditors, employees, turnover and profit. That field list is what separates it from sibling tools like company_filings (documents) or company_profile (registry data), so an agent can route without opening the 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?

It gives a concrete use case with decision questions ('use for supplier and credit checks: is it solvent, how much cash, is it growing') and states an eligibility boundary — most small and medium digital filers work, large companies and groups usually don't. It stops short of naming an explicit alternative tool (e.g. company_insolvency or company_charges) or a when-not-to-use rule, so it is clear context rather than full routing 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structured context: a cost of 2 credits (important for an agent deciding whether to call) and the scope of the record returned, including enforcement/clone risk. It does not discuss failure modes (no match, ambiguous name) or response shape, keeping it out of the 5 band.

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?

Front-loaded with the verb and resource, followed by a compact enumeration of returned fields, then usage and cost. The field list is long but each item is substantive; the only slight redundancy is repeating the identifier options already in the schema.

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 listing what is returned, and it discloses the credit cost and intended decision context. The remaining gap is behavior on name-based lookups — whether multiple firms may match and how ambiguity is handled — which matters for a tool where both identifiers are optional.

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%, with the schema itself stating that name is "used if no frn", so the precedence rule is already documented. The description restates the two identifier options but adds no format, validation, or disambiguation detail beyond the schema. Baseline 3 is appropriate when the schema carries this load.

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 ("Full FCA register check on a financial firm") plus the accepted identifiers (FRN or name), then enumerates exactly what is returned: authorisation status, permissions, trading names, addresses, complaints contact, regulators, client money, fines/enforcement. This makes it clearly distinguishable from the sibling fca_individual (people) and fca_search (lookup), and from the general kyb_check.

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 an explicit use case and audience: "Use before dealing with a bank, lender, broker, adviser, insurer or investment firm, and to spot cloned firms." That is concrete when-to-use guidance. It stops short of naming alternatives (e.g. "use fca_search first if you only have a name") or exclusions, so it falls just below the top band.

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 readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context — the 1-credit cost and the specific contents of the response — which the annotations do not convey.

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 tightly written sentences plus a parenthetical cost note. The identifier and scope come first, then the return payload, then the use case — no filler anywhere.

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 usefully enumerates what comes back, which is the main completeness burden here. It omits only edge-case behavior, such as what happens when the IRN is unknown or the person has no disciplinary 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?

Schema coverage is 100% and the single parameter already documents its type and an example format ('ABC01234'). The description reinforces that this is an individual reference number but adds no syntax, validation, or lookup-failure detail 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 a specific verb and resource ('FCA register check on a person'), the exact key it takes ('individual reference number'), and enumerates the returned data: approval status, current/past regulated roles, firms, and disciplinary history. The person-level scope inherently separates it from fca_firm and fca_search.

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?

'Use to check a financial adviser, mortgage broker or senior manager' gives clear when-to-use context by naming the subject types. It stops short of explicit routing guidance, such as using fca_search when only a name is known rather than an IRN.

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