UK current-account switching offers from each bank's own terms, and a planner for which fit.
Scored across 5 tools
Each tool targets a fairly clear slice: check_offers is a personalized planner/ranking, list_offers is the full catalog, get_offer is a single lookup by id, list_changes is a publication history, and list_savings_and_cashback is explicitly excluded from plans. The main risk is overlap between check_offers and list_offers (both surface offer details), but the descriptions distinguish 'what fits your situation and pays most' from 'everything live'.
All names follow a clean verb_noun snake_case pattern: check_offers, get_offer, list_offers, list_changes, list_savings_and_cashback. Singular/plural noun usage is also principled (get_offer singular, list_* plural).
Five tools is well-scoped for a narrow read-only domain: retrieve all, retrieve one, plan, history, and a separate savings/cashback surface. Nothing feels padded or missing at the count level.
The read-only lifecycle is well covered: catalog, single lookup, personalized eligibility/ranking, change history, and a distinct savings/cashback list. Minor gaps exist—no filtering by bank/provider and no way to fetch a single savings/cashback item—but agents can work around these with list_offers plus get_offer.
Pocketly’s quick check: which offers fit a situation and the order that pays most, with dates and what is left after costs. The same planner and answer as pocketly.co.uk/check. Amounts in pounds. Nothing is stored.
| Name | Required | Description | Default |
|---|---|---|---|
| bank | Yes | Who your current account is with ("other" for any other bank) | |
| cash | Yes | Spare cash you could move for a few days, in pounds | |
| buffer | No | Money to keep untouched, in pounds (default 0) | |
| salary | Yes | A salary of £2,000 or more is paid in each month | |
| cardSpending | Yes | Could use a new card for everyday spending for a couple of months | |
| directDebits | Yes | ||
| householdBills | Yes | At least 2 of the Direct Debits are household bills |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive and closed-world. The description adds real value beyond them: 'Nothing is stored', 'Amounts in pounds', and an assurance the result matches the website planner exactly, which tells an agent the output is deterministic and canonical.
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 the tool's payoff and then the guarantee about storage and currency. No filler, though the phrasing of the first sentence is slightly awkward to parse.
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 the work of explaining return content: the winning order, dates, and residual money after costs. Combined with the strong input schema, an agent has enough to call this 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 coverage is 86%, so almost every parameter is already documented. The description only contributes unit context ('Amounts in pounds') and hints at the buffer concept via 'what is left after costs', leaving the baseline score 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?
The description states a concrete outcome: which offers fit a situation, ranked by payout, with dates and net-of-cost amounts. That is specific enough to distinguish it from list_offers and get_offer, though it never names those siblings 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?
Calling it a 'quick check' and tying it to the pocketly.co.uk/check planner implies when to use it, but there is no explicit when-not-to-use guidance or named alternative for browsing offers versus evaluating them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
One offer by its id (from list_offers or its pocketly.co.uk/offers/ address).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world behavior. The description adds only the id provenance and does not describe not-found behavior or return shape; with annotations covering the safety profile, this is adequate but thin.
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 compact sentence with no wasted words, and the key scoping information is front-loaded.
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 one-parameter read tool with rich annotations and no output schema, the description supplies the essential id source. It could mention error behavior, but nothing critical is missing 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 coverage is 0% and the single id parameter is undocumented in the schema. The description compensates by explaining that the id is an offer id obtainable from list_offers or the pocketly.co.uk/offers/<id> URL, giving meaningful semantics beyond 'string'.
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 retrieval action ('One offer by its id') and scopes it to a single offer, which distinguishes it from list_offers. It does not explicitly contrast with check_offers, but the single-resource focus is 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?
It tells the agent where the id comes from (list_offers or the offer URL), which is useful invocation context. However, it does not state when to prefer this over check_offers or list_offers, nor any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every offer edition Pocketly has published, newest first.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already establish readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful behavior by saying results are published offer editions returned newest first, but it does not explain pagination or how the limit affects the result set.
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 efficient sentence with no wasted wording. It is front-loaded with the resource scope and ordering, though that concision comes at the cost of omitting practical details.
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?
This is a simple read-only listing tool with one optional parameter and no output schema, so the description does not need extensive detail. However, it omits limit behavior and pagination semantics, which are relevant for an agent trying to invoke list_changes 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?
The schema description coverage is 0%, and the only parameter, limit, is not mentioned in the description. The schema provides type and bounds, but the description does not explain what limit controls or how results are paginated, so it does not compensate for the missing parameter documentation.
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 identifies the resource as every published offer edition and states the ordering, newest first. It is clear enough to understand the tool, but it does not explicitly differentiate list_changes from siblings like list_offers or get_offer.
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 description gives no explicit guidance about when to use this tool instead of list_offers, get_offer, check_offers, or list_savings_and_cashback. Usage is only weakly implied by 'offer edition' and 'published'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every live UK current-account switching offer Pocketly holds: what it pays and what Pocketly counts, each condition with the bank’s own words, who can’t get it, and when it was last checked.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Only offers of this kind |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful content-shape context — payouts, conditions in the bank's own words, eligibility exclusions, and a last-checked timestamp — but says nothing about ordering, pagination, or whether stale/expired offers appear.
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 dense, front-loaded sentence that leads with scope and then enumerates the returned content. The phrasing "what Pocketly counts" and "who can’t get it" is colloquial but compact; nothing is wasted.
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 is the only source for return content and it does a decent job of naming the returned facets. However, for a list tool it omits ordering, result-size/pagination behavior, and whether non-live offers are excluded, leaving gaps an agent needs when consuming results.
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 optional enum parameter (kind: switch/premier/joining) is fully documented in the schema. The description never mentions the kind filter and its phrase "Every live ... offer" could briefly suggest there is no filtering, but the schema corrects this, so baseline 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?
States a specific resource with clear scope: "Every live UK current-account switching offer Pocketly holds" tells the agent this is an enumerating read over active switching offers only. It does not explicitly differentiate itself from siblings like get_offer or check_offers, so the agent must infer the list-vs-single distinction from 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?
The description never says when to use this tool rather than check_offers, get_offer, or list_changes, nor does it state any exclusions or prerequisites. The only hint is "Every live ... offer", which weakly implies bulk enumeration, but the agent is left to infer routing from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Savers and cashback from banks’ own pages, never counted in a plan: each with the most it pays by its own terms (or per £1,000 for easy-access savers), in the bank’s words.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a safe, read-only, idempotent operation; the description adds useful behavioral context about data provenance and return semantics. It explains that values come from banks' own pages, are not counted in a plan, and are presented in the bank's own words, with per-£1,000 treatment for easy-access savers.
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 definition is compact and front-loads the resource scope before adding rate-basis caveats. It is somewhat dense and grammatically fragmentary, with a colon and parenthetical clause that slightly reduce immediate clarity.
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?
Given the simple no-parameter shape, read-only annotations, and absence of an output schema, the description supplies enough context about what the returned entries represent and how their values are framed. The main gap is the lack of usage guidance relative to sibling offer 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?
This tool takes zero parameters, so there are no parameter meanings for the description to compensate for. The baseline for a no-parameter tool is 4, and nothing in the description introduces parameter-related ambiguity.
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 identifies the exact resource and scope: savers and cashback sourced from banks' own pages, including how payouts are represented. It does not explicitly state the list action or differentiate from named siblings, leaving the tool name to supply the verb.
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 phrase 'never counted in a plan' hints at an exclusion, but there is no explicit guidance on when to use this tool instead of check_offers, get_offer, list_offers, or list_changes. An agent must infer selection from the resource name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_offersget_offerlist_changeslist_offerslist_savings_and_cashbackBank account terms as banks publish them, dated: fees, waivers, offers. Read-only. Canada today.
US bank, savings and credit-card signup bonuses, each source-checked, with expiry dates.
Read-only access to your own UK bank data: spending, subscriptions, payday plan, net worth.
UK loyalty schemes: what points are worth, bonus points offers now, and where each shop earns.
Add one secure layer between your agents and this server.
