UK Sanctions Screening MCP

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

With no annotations, the description carries the full burden. It does disclose useful behavior: a 200-name cap, that results come back as an audit-ready summary with list version and timestamp, and the 'PRO' tag hinting at a premium tier. It says nothing about authentication requirements, rate limits, or what happens when the cap is exceeded.

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 that front-loads the batch capability; almost every clause carries information. The 'PRO' prefix is minor noise but the rest is efficient.

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 the description partially compensates by describing the return summary (list version, timestamp, audit-readiness). However, for a screening tool with an access_token parameter and a near-identical sibling, it omits auth expectations and tool-selection context, leaving meaningful gaps.

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 threshold ('0-100, default 60') and access_token already documented. The description adds the 200-item cap for names and clarifies that threshold is a match threshold, but does not explain threshold tradeoffs or what values of names are acceptable beyond the examples.

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 ('Screen') and resource ('names'), gives the batch cap (up to 200) and example entity types (customers, suppliers, counterparties), which is far more than restating the name. It does not, however, distinguish itself from the very similar sibling 'global_batch_screen', leaving the agent to guess which batch screener 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?

Beyond the implicit hint that this is for multiple names rather than one, there is no when-to-use guidance, no exclusions, and no pointer to alternatives such as counterparty_check, sanctions_check, or global_batch_screen, despite eleven siblings. The agent must infer routing entirely.

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 must carry behavioral disclosure. It usefully adds paid cost, list coverage, GLEIF resolution, parent screening and match freshness metadata, but does not cover auth requirements, threshold behavior, error/no-match behavior or whether it is read-only.

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 compact and front-loads the cost and core purpose, with no wasted sentences. It is slightly dense in combining scope, parent screening and match metadata, but is appropriately sized.

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 and no annotations, the description needs to be self-sufficient for a 5-parameter tool. It covers purpose, cost, list coverage, resolution path and match metadata, but omits threshold behavior, what happens if neither lei nor name is supplied, and auth expectations beyond the schema.

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 80%, so the schema already documents most parameters. The description adds that lei/name are alternative resolution keys and that lists maps to UK/EU/UN, but threshold and access_token semantics are left to the schema, and no additional format or default guidance is provided.

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 combined action: screen a name against UK/EU/UN sanctions lists and resolve on GLEIF, including parent screening. It is clearer than the name alone and tells an agent this is a composite sanctions+GLEIF check, though it never names or contrasts sibling tools such as sanctions_check or lei_lookup.

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 or when-not-to-use guidance. The mention of 'Global counterparty check' and 'PRO ($0.05)' implies a paid single-counterparty screen, but it does not say to prefer it over sanctions_check, lei_lookup, batch_screen or global_batch_screen.

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 carries the full burden and does well: it discloses the paid cost ($0.05), the exact data source and its limits (only OFAC SDN 'Digital Currency Address' entries), the per-address return fields, and a legal-use caveat. It leaves auth mechanics to the schema's access_token field and says nothing about behavior for non-matching addresses.

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, front-loaded with pricing and scope, with the disclaimer last where it belongs. Dense and free of padding, though the pricing prefix is somewhat prominent relative to the functional description.

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?

No output schema exists, and the description compensates by enumerating the per-address return fields (chain, SDN name, UID, programs, list date, source). Only the no-match behavior and the meaning of the access_token requirement are left implicit.

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 only two parameters, so the schema already documents 'addresses' (up to 100) and 'access_token'. The description restates the 100-address cap but adds no format or validation detail (e.g., accepted chain address formats) 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 ('Screen up to 100 crypto wallet addresses against the OFAC SDN Digital Currency Address entries'), including the exact list screened and the batch limit. It does not explicitly name the singular sibling crypto_address_check as the alternative for single-address lookups, so differentiation rests partly on the name.

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 context is implied by the 'up to 100 addresses in one call' framing and by the screening-aid disclaimer, but there is no explicit when-to-use/when-not guidance or routing to crypto_address_check for single addresses. The legal disclaimer clarifies scope of reliance, not tool selection.

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 carries the full burden and does well: it discloses cost ('FREE'), the exact matching rule (EVM 0x case-insensitive, all others exact), what a hit returns, and a legal-use caveat. Gaps remain on list freshness and whether results are cached or rate-limited, which matters for a compliance-screening tool.

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?

Four tight sentences, front-loaded with 'FREE.' and then the core action, with the caveat last. Every clause carries information an agent needs: coverage, matching rule, return shape, disclaimer.

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 the description compensates by describing the response (match/no match plus SDN name, UID, programs, list date, source). For a one-parameter lookup tool, nothing needed 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 coverage is 100% for the single 'address' parameter, so the baseline would be 3, but the description adds real semantic value by stating that EVM 0x addresses match case-insensitively while other chains must match exactly. That normalization rule is not in the schema and directly affects whether a caller's input will match.

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 (screen) and resource (one crypto wallet address) against a named dataset (OFAC SDN 'Digital Currency Address' entries) with the covered chains enumerated. The word 'one' plus the named dataset cleanly separates it from crypto_address_batch_check and batch_screen without the agent 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?

'Screen one crypto wallet address' implicitly scopes this to single-address lookups, which routes against the batch siblings, and 'FREE' signals there is no cost barrier to calling it. It stops short of explicitly naming when to prefer crypto_address_batch_check, and the 'screening aid only, not legal or compliance advice' line sets expectations without stating any precondition for use.

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 load. It discloses what is returned ('Full record' with named fields) and implies premium/subscriber access via 'PRO.', but says nothing about authorization requirements (the access_token param implies them), error behavior, or rate limits. Adds partial value but leaves meaningful behavioral gaps.

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 sentence plus a tier marker; nothing redundant, and the key information (full record, field list, ID source) is front-loaded. Slightly cryptic abbreviations ('PRO.') prevent a 5.

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 names the return fields, and it identifies the ID namespace. However, for a lookup tool sitting among many overlapping screening siblings, the absence of routing guidance leaves the definition only minimally complete.

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 50% because 'id' has no schema description, but the description compensates by explaining it is a 'UK Sanctions List unique ID' — meaningful semantics an agent couldn't get from the bare string type. The access_token param is documented in the schema itself.

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 combination: returns the full record for a UK Sanctions List unique ID, and enumerates the fields included (aliases, regime, designation date, DOB, nationality). It does not distinguish itself from siblings like global_entity_detail or sanctions_check, so an agent must infer which lookup 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?

Only guidance is the terse 'PRO.' marker, which hints at a subscription tier but doesn't say when to use this versus sanctions_check (screening) or global_entity_detail (non-UK lists). No exclusions or prerequisites are 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?

With no annotations, the description carries the burden and does disclose cost ($0.05), the 100-name batch ceiling, the three list sources, and that results are per-name best matches with list version, date and freshness. It omits matching semantics (fuzzy vs exact), how ties are resolved, and any failure/partial-result behavior when a name gets no hit.

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 with the cost marker leading and no filler; every clause carries information. Density comes at a cost — abbreviations like 'FSF' and 'date and freshness' are terse to the point of ambiguity.

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-param paid batch tool with no output schema, the description gives a partial return picture ('per-name best match with list version, date and freshness') but leaves threshold semantics, 'lists' value format, and any output shape undefined. An agent can call it, but not tune or interpret it 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?

Schema coverage is only 25% — only access_token is documented. The description implicitly covers 'names' and 'lists' (naming the three regimes), but 'threshold' is a semantically load-bearing matching cutoff left completely unexplained, and no valid values are given for 'lists' (e.g. whether omitting it means all three).

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 ('Screen up to 100 names') plus the covered regimes (UK, EU FSF, UN) and the batch cap, which is far more than a restatement of the name. It does not, however, distinguish itself from the sibling 'batch_screen' or 'sanctions_check', so an agent cannot tell from the text which of these overlapping tools 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?

The 'up to 100 names in one call' phrasing weakly implies bulk use, but there is no explicit when-to-use, when-not-to-use, or routing to 'batch_screen'/'sanctions_check'/'counterparty_check'. The '$0.05' PRO marker hints at a cost tradeoff without stating the alternative.

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 behavioral burden. It does disclose the $0.05 paid cost and the shape of what comes back (list version, date, freshness), which is valuable, but it says nothing about permissions/subscriber token requirement, rate limits, or error behavior for unknown references.

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 sentence with the cost front-loaded and the accepted ID regimes enumerated before the return contents. Nothing is padded and no clause is redundant.

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 give a minimal return-value sketch (list version, date, freshness), which is more than many. Still missing for a paid lookup tool: what a 'full record' actually contains, auth expectations, and failure modes for a reference not found.

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 50% (id is bare), but the description compensates by supplying concrete accepted identifier formats (EU.27.28, CDi.001) and mentioning UK unique IDs. It adds real meaning beyond the schema for the undocumented required parameter.

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 ('Full record') and constrains the input to EU FSF, UN, or UK unique reference identifiers with concrete examples. It partially separates itself from siblings like entity_detail and lei_lookup by naming the identifier regimes it accepts, though it never explicitly contrasts with them.

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 by the input formats ('use this when you hold an EU.27.28-style or CDi.001-style reference'), and the PRO/$0.05 tag hints at a paid tier. No explicit when-not-to-use guidance or named alternatives among the ten sibling tools are 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?

With no annotations, the description carries the full burden and does reasonably well: discloses that access is free, that name lookups return only the top 3 matches (a result cap the agent must know about), and lists the fields returned even without an output schema. It omits error/no-match behavior and any rate or auth expectations.

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 leading 'FREE.' marker, front-loaded with the source system and the two modes. Every clause carries new information — cost, input formats, result cardinality, return fields.

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-param, no-annotation, no-output-schema tool, this covers inputs, cost, result cap, and returned fields — enough to invoke correctly. Missing only edge-case behavior (no matches, invalid LEI) and parameter precedence when both are passed.

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%, so the description must compensate, and it does: 'lei (20 chars)' gives a concrete format constraint, and 'name' is explained in terms of its output behavior (top 3 GLEIF matches with fields). It stops short of stating whether the two params are mutually exclusive or which wins if both are supplied.

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 specific resource (GLEIF LEI registration record) and the verb (lookup), and describes both operating modes — lookup by LEI vs. by company name. It doesn't explicitly contrast itself with siblings like entity_detail, but the LEI/GLEIF scope is distinctive enough for an agent to place 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?

States the two entry paths clearly: pass a 20-char LEI for a full record, or a company name for top 3 matches. That is actionable conditional guidance, though it says nothing about when to prefer this over entity_detail or sanctions_check.

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 carries the full behavioral burden, but it only says 'PRO' and names filters. It does not disclose pagination, default behavior when no filters are supplied, authentication needs beyond the schema token note, or what the response 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?

The description is a single tightly packed sentence with the key filters front-loaded and no redundant material. Its terseness creates completeness gaps elsewhere, but as a conciseness matter there is no waste.

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 four-parameter list endpoint with no annotations and no output schema, the description is too thin. It omits return format, default limit behavior, what happens with no regime or since filter, and how the premium 'PRO' gating works.

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 50%: since and access_token are documented in the schema, while regime and limit are undocumented there. The description adds useful regime examples and clarifies that since means 'designated since a date,' but it does not explain limit at all.

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 returns designations filtered by regime and/or designation date, with examples like Russia and Iran. It does not explicitly distinguish itself from sibling screening/check tools, but the resource and filters are clear.

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 guidance on when to use this tool versus siblings such as sanctions_check or entity_detail, nor any prerequisites or exclusion conditions. The 'and/or' phrasing implies optional filters but does not explain usage context.

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 burden. It usefully discloses that it is free and that it returns the best 3 matches with a score, but says nothing about match semantics (fuzzy vs exact), thresholds, rate limits, or auth requirements for a compliance-critical screen.

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 with zero waste. The cost signal ("FREE") is front-loaded and the return shape follows immediately.

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 screening tool with no annotations and no output schema, the description covers purpose, cost, and return shape, but leaves the agent guessing on match semantics, score scale, and any request constraints 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 one parameter at 0% schema coverage, the description must compensate. It clarifies that the "name" input accepts a person or company name, which adds real meaning, but does not specify accepted formatting (e.g., full name vs first/last split).

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 ("Screen") and resource ("UK Sanctions List (FCDO/OFSI)"), with a clear scope of "one person or company name". The "one" scope and "UK" qualifier implicitly distinguish it from batch_screen and global_batch_screen, though 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?

The single-name and UK-list scope implies when this tool applies vs batch and global siblings, and "FREE" signals no-cost screening. However, there is no explicit when-to-use / when-not-to-use statement or named alternative, leaving routing 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?

With no annotations, the description does useful work by disclosing cost ($0.01, PRO tier) and the 500-item cap, plus the validation standard applied. It does not say what happens to failing pairs (partial response? per-item errors?), whether the call is read-only, or what the auth/subscription requirement entails beyond the schema's access_token field.

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 tier and price, then capability, then limit and rationale. No waste, though leading with price rather than the operation is a slightly awkward ordering.

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 paid batch validation call with no output schema and no annotations, the description should say at least what comes back per pair and how invalid entries are handled. It covers cost, limit and ruleset but leaves the response contract unstated.

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 50%, but the description supplies the single most important constraint not encoded in the schema: the hard limit of 500 accounts per call. It doesn't further clarify pairing or formatting rules, which the nested schema already covers.

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 (Validate) and a precise resource (UK sort code + account number pairs), plus the rule set used (Vocalink/Pay.UK modulus). The 500-pair batch scope implicitly distinguishes it from the single-pair sibling sort_code_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?

The parenthetical 'e.g. before a Bacs run or payee import' gives real usage context, but there is no explicit guidance on when to prefer this over sort_code_check or what to do with single lookups.

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 carries the full burden, and it does add real value: free of cost, no external lookup (deterministic, local computation, no data leaves the system), and the specific algorithmic standard applied. It is silent, however, on what happens with an invalid input or what the validation result conveys (pass/fail only, or a reason code), which matters most for an agent deciding whether to call it.

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 clauses, front-loaded with the free/no-lookup qualifiers before the core purpose. No sentence is padding; the examples of modulus variants are the only elaboration and they are the informative part.

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 deliberately narrow two-parameter validator with full schema coverage and no output schema, the description supplies purpose, cost model, and dependency profile. The remaining gap is return semantics, which the absence of an output schema leaves 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%, with 'sort_code: 6 digits, e.g. 20-00-00' and 'account_number: 6-10 digits' already spelling out format and length. The description adds nothing about parameter semantics beyond the schema, so the baseline of 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?

Names a specific verb and resource ('Validate one UK sort code + account number') plus the exact rule set applied (Vocalink/Pay.UK modulus checking, MOD10/MOD11/double-alternate and exceptions). The word 'one' cleanly separates it from the sibling sort_code_batch_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?

Usage is only implied: 'one' signals single-record scope versus the batch sibling, and 'No outside lookup' signals a self-contained check. It never states when to prefer it over sort_code_batch_check or what prerequisite state an agent needs, so the routing decision 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.