site

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 discloses the return payload well, which is the main thing an agent needs for a zero-parameter metadata read, but says nothing about auth requirements, caching, or whether the 'provenance banner' is static or computed.

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 tight sentences with the operational instruction ('Call this first') front-loaded ahead of the payload list. The first sentence is a comma-heavy noun phrase rather than a verb-led statement, which costs a little readability.

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 annotations and no output schema, the description is the only source of return-value information, and it enumerates the fields returned. That is sufficient for a trivial zero-param introspection call, though the overlap with dataset_provenance is left unresolved.

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 tool takes zero parameters, so there is nothing to misinterpret and the baseline for a parameter-free tool applies. The description correctly spends no words on inputs.

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 (columns, numeric flags, row count, provenance banner) for a named dataset, which is more specific than the title alone. It is distinguishable from dataset_stats and dataset_row, though the 'provenance banner' overlaps with the dataset_provenance sibling and is not disambiguated.

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?

'Call this first to learn the schema' gives explicit ordering guidance that no sibling provides. It still offers no when-not guidance or explanation of why this precedes dataset_stats or dataset_provenance rather than duplicating them.

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 disclosure burden, and it delivers little beyond the ordering behavior ('in the order given'). It does not state that the call is a read-only lookup, any permission/scope requirements, error behavior for unmatched values, or anything about the result shape.

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 tightly-sized sentence with no filler, and the core selection logic is front-loaded before the use-case hint. The phrasing is slightly awkward as a noun fragment, but 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?

For a simple two-parameter read with no output schema and no annotations, the description covers purpose, both parameters, and intended use. It is adequate but missing basic completeness items such as confirmation that it is a read operation and any hint at the returned row shape, given there is no output schema to fall back on.

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 explain both parameters, and it does so reasonably: 'column' is the field matched against, 'values' are the values matched, with result order following input order. It still leaves gaps, notably whether 'column' expects a column name vs. index and what the valid column set is.

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 operation on a specific resource: retrieving rows of the Bank Code Lookup dataset selected by column/value match. The 'for X vs Y questions' cue gives the agent a clear sense of intent that distinguishes it from generic lookups. It stops short of naming the sibling tools (dataset_search, dataset_top) it competes with, so it does not fully disambiguate within the family.

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 trailing 'for X vs Y questions' clause signals the intended use case, which is genuine context beyond the schema. However, it offers no explicit when-not, prerequisites, or named alternatives among the many dataset_* siblings, leaving the agent to infer boundary cases.

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 burden. It discloses that this is a read-only metadata lookup by framing it as something to 'read' and by describing static provenance content, not a mutation or computation. It could say more about whether it is always available or how the data is refreshed, but for a zero-parameter informational tool it is reasonably transparent.

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 tight sentences, front-loaded with the returned fields and closing with the purpose. Nothing is redundant or misleading.

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 no-input, no-output-schema metadata tool, the description covers what the agent needs: what it returns and why to call it. No additional behavioral details are necessary 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?

Zero parameters, so the baseline is 4. The description correctly implies no filtering or input is needed by presenting the tool as a fixed read of dataset-level metadata.

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 resource (Bank Code Lookup dataset) and enumerates exactly what it returns: source, computation date, licence, and citation. It is clearly differentiated from siblings like dataset_stats or dataset_columns, which provide analytical or structural views rather than provenance.

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 clear condition for use: 'Read this to attribute a figure correctly.' That tells the agent when this tool is the right choice, though it does not explicitly name alternatives or exclusions.

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 discloses the case-insensitive matching semantics, but says nothing about what is returned (single row vs many), result limits, or error behavior when no match exists — gaps that matter for an un-annotated read 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?

A single well-formed sentence with the dataset and the matching rule front-loaded. Nothing is wasted, though it is arguably under-specified rather than genuinely concise.

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 must explain the return shape, and it does not. An agent knows how to match but not what it receives back or what columns exist, which is thin for a two-parameter lookup tool in a family of dataset 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 0%, so the description is the only source of meaning. It does clarify that 'column' selects a dataset column and 'value' is compared to it case-insensitively, but it does not say what column names are valid or constrain the value format, leaving both parameters only partially explained.

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+resource (return the rows of the Bank Code Lookup dataset) and pins the matching rule (column equals a value exactly, case-insensitive). It reads as a clear exact-match lookup, contrasting implicitly with the fuzzier dataset_search sibling, though it never names that sibling to make the distinction explicit.

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 implied rather than stated: 'exactly (case-insensitive)' signals this is the exact-match path versus a search tool. There is no explicit when-to-use, when-not, or named alternative among the nine sibling tools.

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. It usefully discloses that matching is case-insensitive and capped at 50 rows, but says nothing about result ordering, pagination, permissions, or what happens when cells match partially.

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 identifies the dataset, the matching rule, and the result bound with no wasted words.

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 two-parameter search with no output schema and no annotations, the description covers the essentials but omits return shape and ordering. Adequate but with clear gaps for an agent that needs to know what a result row looks like.

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% — query is documented in the schema, limit is not. The description compensates by explaining matching semantics (case-insensitive) and the 'up to 50' cap, which conveys limit behavior, so it adds value but does not fully describe the limit parameter's role or default.

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 (search) and resource (rows of the Bank Code Lookup dataset) plus the matching rule and result cap. It is clear what the tool does, though it never names sibling tools like dataset_top or dataset_row, so differentiation from them is left to inference.

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 guidance on when to use this search versus dataset_top, dataset_row, or dataset_stats. A reader can infer it is for text lookup, but no condition, prerequisite, or alternative is 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 full burden and does meaningful work: it discloses that grouping commas and currency symbols are handled and that non-numeric rows are excluded but counted. It omits error behavior (e.g. what happens for a non-numeric or nonexistent column) and confirms nothing about read-only safety, keeping it short of a 5.

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 dense sentence that front-loads the returned metrics and appends the caveats in a parenthetical. No filler, everything earns its place.

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, so the description usefully enumerates the returned metrics, which is the key missing piece an agent would need. It leaves minor gaps around failure modes and result typing, but is otherwise sufficient for a one-parameter aggregation tool.

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% for the single 'column' parameter, so the description must compensate. It adds one real constraint (the column must be numeric) but never states expected identifier format, case sensitivity, or how the column is referenced, so compensation is only partial.

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 precise operation (count, min, max, mean, median, sum) on a precise resource (a numeric column of the Bank Code Lookup dataset), so the agent knows exactly what will be computed. It doesn't explicitly contrast itself with siblings like dataset_top or dataset_columns, but the statistics scope makes the distinction inferable.

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 implied: it is the tool to call when summary statistics of a numeric column are needed, and the parenthetical restricts input to numeric columns. There is no explicit when-to-use/when-not guidance or named alternative for non-numeric columns (e.g. pointing to dataset_top or dataset_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?

With no annotations, the description carries the full burden. It does add useful behavioral context: the operation is directional (highest vs lowest), operates on a numeric column, and is scoped to the Bank Code Lookup dataset. It is silent on tie-breaking, null handling, non-numeric column errors, and what is actually returned, which are meaningful gaps for an unannotated 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?

One sentence, front-loaded with the core operation and the resource before the illustrative quote. No filler, though the trailing em-dash example is slightly less economical than folding the intent into the main clause.

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 should ideally note the return shape (a small ranked set of rows) and edge behaviors. It conveys scope and direction adequately for a simple ranking tool but leaves the agent guessing about output and tie/default behavior.

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 only 33% (only 'ascending' is annotated), so the description must compensate. It does clarify that the column must be numeric and ties the direction to highest/lowest, but it says nothing about 'limit' or the 1-50 bound, leaving part of the parameter surface unexplained.

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 verb (rank/return highest or lowest rows), the resource (Bank Code Lookup dataset rows), and the keying dimension (a numeric column), so an agent can grasp the operation immediately. It does not explicitly differentiate itself from close siblings like dataset_stats or dataset_row, which keeps it from 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?

The quoted framing "which is the most/least X" implies the intended use case and gives the agent a mental trigger for when to reach for this tool. However, it names no alternatives (e.g., dataset_stats for distribution, dataset_row for lookup) and states no exclusions, so usage is only implied rather than spelled out.

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 disclosure burden and does well: it states nothing is bought, ordered or paid, that no quote is guaranteed, and that it is free, which establishes the non-committal, side-effect-free nature of the enquiry. It also previews the returned content (recipients, consent wording, confirmation flow). It stops short of stating whether calling it has any side effects itself or its exact response shape.

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 'Read first.' and then kept to a short set of clauses. The phrasing 'Nothing is bought, ordered or paid' is slightly redundant with 'not a purchase' in the title, but there is little waste overall.

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, so the description partially compensates by naming what is returned (who receives details, consent wording, how the person confirms). Combined with the zero-param schema and the clear non-committal framing, this is adequate, though it could say more about the exact response structure.

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 tool takes zero parameters, so there is nothing to document and no parameter ambiguity exists. Baseline for a no-param tool is 4; the description adds nothing needed here and nothing misleading.

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?

It identifies itself as a read-first describe tool and specifies the resource it documents (an enquiry with human providers on Bank Code Lookup), which distinguishes it from the sibling submit_enquiry that actually creates the enquiry. The framing is slightly indirect ('states plainly what submit_enquiry does') rather than describing itself directly, but an agent can still tell what this tool returns.

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?

'Read first' implies this should be consulted before submit_enquiry, which is useful ordering guidance. However, there is no explicit statement of when-not to use it, and it never names submit_enquiry as an alternative in a routing sense ('use X instead'), so usage is implied rather than spelled out.

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 burden. It discloses the shape of what is returned and the key-based contract with submit_enquiry, but says nothing about performance, rate limits, permissions, or whether results are cached/static for a fixed enquiry.

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, front-loaded with the deliverable and followed by the actionable tie-in to submit_enquiry. No filler or redundant restatement of the title.

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 the returned field attributes, which is what an agent needs to consume the result. It is slightly incomplete in not clarifying how 'the Bank Code Lookup enquiry' is identified given the tool takes no inputs, leaving open whether other enquiries are reachable.

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 tool takes zero parameters and the schema is empty, so there is nothing to disambiguate; baseline 4 applies. The description correctly conveys that the field list is not parameterized by any input.

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 concrete resource and enumerates its contents (key, label, type, required, help text, allowed options), so an agent knows this returns field metadata rather than data rows. It routes to submit_enquiry for the follow-up step, but it never distinguishes itself from the neighboring enquiry_describe or dataset_columns tools, which is the main ambiguity.

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 implies the workflow — fetch fields, then 'Pass answers to submit_enquiry keyed by field key' — which is genuinely useful sequencing guidance. However, it gives no explicit when-to-use versus enquiry_describe/dataset_columns and no prerequisites (e.g., whether an enquiry must be selected first), so usage is only implied.

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 so: it discloses validation behaviour, the returned summary/consent line/confirmation token, the requirement that the recipient click an email link before any provider sees the enquiry, and the exact consent wording shown at step 1. The no-third-party-sharing and email-notification side effects are explicit.

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 critical scoping statement ('NOT a purchase') and cleanly segmented into Step 1/Step 2. The quoted consent sentence is fairly long and repeated in the schema, so there is minor redundancy, but every clause carries operational meaning.

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 mutation-style, two-phase tool with no output schema and a nested answers object, the description supplies what the return of each call contains, the gating conditions, and the consent contract. Nothing an agent needs to execute the flow 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%, but the description still adds real meaning: 'answers' is keyed by field key obtained from enquiry_fields, 'consent' must be true only after the person has read the quoted consent text, and 'confirmation' is the token returned by step 1 after approval. This explains the cross-call relationship between the two invocations, which the schema cannot.

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 (submits) and resource (enquiry to Bank Code Lookup) and immediately draws the boundary that it is NOT a purchase or guaranteed quote. It references the sibling enquiry_fields as the source of field keys, so an agent can distinguish it from the other enquiry_* tools without opening schemas.

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 two-step protocol: step 1 validates and returns a summary/consent/token, step 2 is only called if the person agrees, with the exact parameter set for each call. It also names the prerequisite field source (enquiry_fields) and the human-approval condition, leaving nothing to inference.

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