site

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

No annotations are provided, so the description carries the behavioral burden. It discloses the returned data (columns, numeric flags, row count, provenance banner), which implies a read-only metadata call, but never states that explicitly, nor mentions cost, auth, or side effects.

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: one enumerating the payload, one stating the call ordering. No filler, and the usage directive sits at the end where it is easy to catch.

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 does the work of describing returns and when to call. It is complete for a zero-argument metadata tool, though it could note that the result is static/read-only to fully cover the behavioral gap.

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 for the description to disambiguate beyond what the schema provides. Baseline 4 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 precise verb-and-resource ('The columns... row count... provenance banner of the Working Capital Quotes dataset') and enumerates exactly what it returns. An agent can distinguish it from dataset_stats or dataset_provenance by the explicit content list.

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?

Explicitly directs 'Call this first to learn the schema,' giving the agent a clear ordering cue relative to the sibling exploration tools. It stops short of naming when-not-to-use it or pointing to the alternatives by name, but the sequencing guidance is unambiguous.

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, yet it only implies read-only retrieval and discloses order preservation. It says nothing about what happens when a value matches no rows, whether results are paginated, or how many rows are returned, and it does not mention the 10-value cap.

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 compact sentence with the resource and matching rule front-loaded and the use case appended after an em dash. It is slightly fragment-like (no verb) but wastes no 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 retrieval tool with no output schema and no annotations, the essentials (dataset, filter semantics, ordering, intent) are covered. However, return shape, missing-value behavior, and the values cap are absent, leaving meaningful gaps the agent must guess at.

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%, but the description does explain both parameters semantically: 'column' is the filter attribute and 'values' is an ordered list to match against, with matching being 'any of'. It does not convey the 2–10 item constraint enforced by the schema, so it only partially compensates for the coverage gap.

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 the concrete resource (rows of the Working Capital Quotes dataset) and the selection rule (column equals any of the given values, in the given order). The 'for X vs Y questions' clause gives an intent that helps distinguish it from dataset_row (single row) and dataset_stats, though it never uses an explicit verb and doesn't clearly separate itself from dataset_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?

The trailing 'for "X vs Y" questions' clause implies the use case, which is the only usage guidance present. There is no explicit when-not guidance and no sibling alternative named (e.g., dataset_search or dataset_row), so the agent must infer selection criteria itself.

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. The word 'Read' implies a non-mutating lookup with no side effects, which is the key behavioral fact for a zero-parameter tool, but read-only status is never stated explicitly and no auth, rate-limit, or scope caveats are mentioned.

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, no filler. The returned fields are front-loaded in the first sentence and the usage cue follows, so an agent scanning the first line already knows what it gets.

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 must convey the return payload, and it does so by enumerating source, computed date, licence, and citation. It stops short of describing the shape or format of the citation field, but that is a minor omission for a fixed-metadata endpoint.

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 per the rubric this is a baseline 4. There is no parameter semantics to explain, and the description correctly does not invent any.

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 resource (provenance metadata for the Working Capital Quotes dataset) and enumerates the four things it returns: source, compute date, licence, citation. The verb is implicit ('read this') rather than stated, but the scope is unambiguous and clearly distinct from siblings like dataset_stats or dataset_columns.

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 this to attribute a figure correctly' gives a concrete triggering condition for the agent. It does not name alternatives (e.g. dataset_columns for structure), but for a zero-parameter metadata lookup the use case is narrow enough that no exclusions are needed.

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 must carry the full behavioral burden. It usefully discloses that matching is exact and case-insensitive and that the result set is 'rows' (potentially more than one, despite the singular title). It omits row limits, permissions, and return shape, which matter for a lookup tool with no output 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?

A single, front-loaded sentence with no filler; the dataset scope and exact-match condition come first. It is efficient, though the brevity leaves no room for the usage routing a lookup tool would benefit from.

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 lookup this covers the core semantics, but with no annotations and no output schema the description should say more about result behavior (how many rows, ordering, limits) and about when to prefer this over the other dataset_* retrieval 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 must compensate for the undocumented 'column' and 'value' parameters. It does explain their relationship (column equals value) and the case-insensitive comparison semantics, but adds no format or naming conventions for column identifiers or allowed value types.

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 the exact operation (return rows where a column equals a value) and the resource (Working Capital Quotes dataset rows), so an agent can tell it is an exact-match lookup rather than a general query. It does not, however, differentiate itself from siblings like dataset_search or dataset_compare, leaving the agent to infer the boundary.

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 word 'exactly' implies this is the tool for precise key lookups as opposed to fuzzy retrieval, which is usable implied guidance. There is no explicit when-to-use statement, no exclusions, and no named alternative (e.g., dataset_search) for non-exact queries.

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, and it does disclose the case-insensitivity of matching and the result cap. However, it omits ordering of results, default limit behavior, permissions, and empty-result behavior, which matter for a search tool with zero annotation coverage.

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 that states resource, match semantics, and cap without filler. Efficient, though the result cap placement at the end is slightly awkward and could be paired with ordering information.

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 and no annotations, so the description is the only source of return-shape information. It implies rows are returned but does not state ordering, whether truncation occurs beyond the cap, or the default limit, leaving meaningful gaps for a no-output-schema 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 coverage is 50%: query is documented in-schema ('text to look for in any cell'), while limit has only min/max bounds and no description. The description usefully adds case-insensitivity for the query, but never clarifies the limit's default or how truncation is signalled.

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 (search) plus resource (rows of the Working Capital Quotes dataset) and matching semantics (cells contain the query, case-insensitive). An agent can distinguish it from the dataset_* siblings only by inference, since no sibling is named as an alternative.

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?

No when-to-use, when-not-to-use, or alternative routing is stated. With siblings like dataset_top, dataset_row, and dataset_stats nearby, the description gives no signal about which one to pick for which need; usage must be inferred from the name alone.

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 disclose genuinely useful behavior: grouping commas and currency symbols are handled, and non-numeric rows are excluded from the aggregate but still counted. It stops short of stating the return format, whether the call is read-only, or how missing/empty columns behave.

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 that front-loads the output list and appends the two important data-handling caveats in parentheses. No filler, though the leading stat enumeration delays the 'what it does' framing slightly.

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 explain what comes back by enumerating the returned statistics, and it flags the two data quirks that affect correctness. For a one-parameter read tool this is close to sufficient; only the behavior on an all-non-numeric column is 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 coverage is 0% for the single 'column' parameter, so the description must compensate. Saying the column must be numeric is the only real constraint it adds; it does not say whether the value is a header name, where valid names come from (dataset_columns), or how a non-existent column is handled.

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 the exact resource (summary statistics of a numeric column) and enumerates the six stats returned (count, min, max, mean, median, sum), scoped to the Working Capital Quotes dataset. That is specific enough to separate it from dataset_top and dataset_compare, though it never explicitly contrasts with those siblings.

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 when-to-use or when-not-to-use guidance and no alternative tool is named. The phrase 'numeric column' implicitly constrains the input, but an agent gets no help deciding between this and dataset_top, dataset_compare, 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?

No annotations are supplied, so the description carries the full disclosure burden and mostly fails it. It never states that this is a read-only operation, what a tie in the ranked column yields, whether results are truncated silently, or what the response looks like.

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 the ranking concept front-loaded and no filler. The em-dash quote is stylistic rather than wasteful, though it delays the concrete parameter behavior.

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, no annotations, and an undocumented `limit`, the description should supply the missing operational detail (default row count, result shape, tie handling, read-only nature) but does not. It is only adequate for understanding the concept, not for calling the tool 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 description coverage is only 33% (just `ascending`), and the description adds little: 'by a numeric column' restates `column` and 'highest (or lowest)' roughly duplicates the documented `ascending` semantics. The `limit` parameter is entirely undocumented in both schema and description, including its default and its cap of 50.

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 concrete verb+resource+scope: the highest/lowest rows of a specific dataset ranked by a numeric column, with an intuitive restatement ("which is the most/least X"). It is clearly distinguishable from dataset_stats (aggregation) and dataset_row (single row), though it never names a sibling 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 'which is the most/least X' framing implies the analytical question this tool answers, so usage is inferable. However there is no explicit when-to-use versus dataset_stats, dataset_search, or dataset_compare, and no stated prerequisite that the column must be numeric-typed.

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 present, so the description carries the full burden, and it does disclose key behavioral facts: nothing is bought/ordered/paid, no quote is guaranteed, and it is free. It also enumerates what the response contains (recipients, consent wording, confirmation step), which is genuinely useful. It could additionally state that the tool itself is a read-only, side-effect-free description call.

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 framing ('Read first', what you get). The middle clause repeats the title's disclaimers slightly, but overall each sentence contributes meaning without bloat.

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 parameters, no annotations and no output schema, the description carries the disclosure burden and covers what the tool returns (recipient info, consent wording, confirmation flow) and the non-binding nature of the enquiry. That is nearly complete for an informational tool; only the returned content's structure/format is unspecified.

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 the baseline is 4; there is nothing for the description to disambiguate. Schema coverage is 100% and the empty object confirms no inputs are expected.

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 artifact ('an ENQUIRY with a human') and explicitly contrasts it with a purchase or guaranteed quote, then states it documents what submit_enquiry does. An agent can tell this apart from submit_enquiry itself. It is slightly indirect about being a documentation/meta tool, but the title plus description together make the resource 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?

'Read first' implies an ordering relative to submit_enquiry, which is useful sequencing guidance. However, no explicit when-to-use/when-not statement is given and no alternative sibling (e.g. enquiry_fields) is named as a comparison point, so it remains implied rather than 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 behavioral burden. It does add real value by enumerating the returned attributes in lieu of a missing output schema, which is effectively a return-shape disclosure. However, it says nothing about access requirements, whether fields vary by enquiry, or error behavior.

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, zero filler. The content statement comes first and the downstream usage instruction second, which is the right front-loading for a schema-discovery tool.

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 zero-parameter read tool with no output schema, the description is close to sufficient: it lists the returned fields and tells the agent how to use the keys. It stops short of naming when to prefer this over enquiry_describe, which is the only meaningful remaining gap.

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 the baseline of 4 applies. The description does not need to compensate for any parameter gap.

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 names a specific resource (every field of the Working Capital Quotes enquiry) and enumerates the attributes returned (key, label, type, required, help text, allowed options), which is far more specific than a tautology. It also distinguishes itself from submit_enquiry by naming it as the consumer of the returned keys, though it never states the retrieval verb 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 instruction 'Pass answers to submit_enquiry keyed by field key' implies the workflow (fetch fields, then submit) but gives no explicit when-to-use rule, no conditions, and no contrast with enquiry_describe, the other enquiry sibling. Usage is inferable but not 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 provided, the description carries the full behavioral burden and does so: it discloses the two-step validate-then-submit flow, that step 1 only validates and returns a summary/consent line/token, that submitting triggers an email with a mandatory click-through before any provider sees the details, and the exact consent semantics. These are side effects and workflow constraints an agent could not derive from the schema alone.

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 most important qualifier ('NOT a purchase') is front-loaded and each sentence carries procedural information. It is somewhat long and the consent wording is duplicated verbatim from the schema's consent description, which is minor redundancy rather than bloat.

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, but the description compensates by naming what step 1 returns (summary, consent line, confirmation token) and what happens after step 2 (email with a required link). For a two-phase, consent-gated submission tool, this is complete enough to drive correct use.

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 already 100%, so the baseline is 3, but the description adds workflow meaning the schema does not: 'answers' must be keyed by field key from enquiry_fields, and 'confirmation' is a token obtained from step 1 only after approval. That sequencing context materially improves correct invocation of the optional third 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 and resource ('Submits an enquiry to Working Capital Quotes') and immediately disambiguates with negative scope ('NOT a purchase, NOT a guaranteed quote'), which separates it from read-only siblings like enquiry_fields and enquiry_describe. An agent can tell exactly what this tool does before 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 lays out explicit sequencing: Step 1 call with answers and consent=true, Step 2 call again with the same answers plus the confirmation token only after the person agrees. The gating condition ('only if the person agrees') and the prerequisite (token from step 1) are stated outright, 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.