site

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

No annotations are provided, so the description carries the burden. It implicitly conveys a pure read operation with no parameters and no side effects, which is reasonable disclosure for a zero-arg introspection tool, but says nothing about cost, caching, or whether output is static or refreshed.

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 short sentences, zero filler, with the content list front-loaded and the usage directive placed last where it belongs. Every clause 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?

With no output schema and no parameters, the description must name the return fields, which it does exhaustively (columns, numeric classification, row count, provenance banner). It is close to complete; only the relationship to overlapping siblings 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?

The tool takes zero parameters, so there are no parameter semantics to document; baseline 4 applies. The description correctly does not invent or discuss arguments.

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 the specific resource (the Contractor Lead Quotes dataset) and enumerates the returned content: columns, numeric flags, row count, provenance banner. It is clear against most siblings, though the 'provenance banner' overlap with the sibling dataset_provenance is not resolved.

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 an ordering hint, which is genuine usage guidance. However, it does not say when to prefer dataset_stats (row count overlap) or dataset_provenance (provenance banner overlap), both of which appear to duplicate part of this tool's output.

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 of behavioral disclosure. It adds the ordering behavior ('in the order given') and the any-of matching semantics, but does not state that it is a read-only query, nor does it mention result limits, pagination, 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?

It is a single, tight sentence with no wasted words, and it front-loads the resource and filter condition. The fragmentary phrasing and em-dash aside are efficient but slightly reduce readability compared to a clean full sentence.

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 filter tool with no output schema and no annotations, the description covers what is returned and the primary use case. It leaves out when to prefer alternatives, safety profile, and parameter constraints, so it is minimally complete but not fully self-contained.

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 0% schema description coverage, the description must compensate. It explains that 'column' selects the column to filter and 'values' are the values to match, and notes that output follows the given order. It does not explain the string type, minimum/maximum item constraints, or that column must be a non-empty 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 identifies the specific dataset ('Contractor Lead Quotes') and the filtering condition ('column is any of the given values'), and signals the use case 'for X vs Y questions'. It stops short of naming a verb like 'compare' or distinguishing itself from siblings such as dataset_search, so it is clear but not sibling-differentiating.

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 when to use it by stating 'for X vs Y questions', which is a contextual usage hint. However, it does not explicitly say when to use this tool instead of alternatives like dataset_search or dataset_row, leaving the agent to infer.

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 so reasonably: it lists the exact metadata returned (source, computed date, licence, citation), implying a side-effect-free read. It omits any auth/permission notes, but for a zero-parameter metadata fetch the main behavioral question — what comes back — is answered.

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 short sentences, with the returned fields front-loaded and the actionable instruction second. No filler or redundancy; every clause carries 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?

With no output schema, the description is obligated to describe what is returned, and it does so completely. The only gap is the hardcoded "Contractor Lead Quotes dataset", which leaves unclear whether this tool is scoped to a single dataset or generalizes across the dataset_* family.

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 defines zero parameters (100% coverage of an empty object), so per the baseline there is nothing for the description to explain. No misleading input assumptions are introduced.

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 enumerates exactly what the tool surfaces (source, compute date, licence, citation) for a named dataset, which is more concrete than the title alone. It does not name or differentiate from any sibling, but no sibling appears to overlap with provenance/attribution content, so confusion risk is low.

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 clear triggering context for use. It stops short of explicit exclusions (e.g. “for column definitions use dataset_columns”), but the purpose is narrow enough that the intended usage 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?

With no annotations, the description carries the full burden. It usefully discloses the matching semantics (exact, case-insensitive) and that the dataset is fixed, but says nothing about read-only behavior, pagination, result limits, or what happens when multiple or zero rows match.

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 no filler; the dataset scope and match condition are 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 two-parameter lookup with no annotations, no output schema, and no parameter descriptions, the definition covers intent and match semantics but omits return shape (which columns come back), multi-match behavior, and column-name sourcing. Adequate but with clear 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 0% for two required parameters, so the description must compensate. It clarifies that 'column' is a column of the Contractor Lead Quotes dataset and how 'value' is matched, but never says where valid column names come from (e.g. the dataset_columns sibling) or what datatypes are accepted.

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 operation: returning rows of the Contractor Lead Quotes dataset where a column equals a value. The phrase 'equals a value exactly (case-insensitive)' implicitly distinguishes it from the fuzzy/semantic sibling dataset_search, 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?

Usage is only implied: the word 'exactly' signals this is for known-key lookups rather than broad search, but the description never says when to prefer this over dataset_search or dataset_top, nor states any preconditions.

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 full burden. It usefully discloses match semantics (case-insensitive, any cell) and a result cap ('up to 50'), which is real behavioral context. However, it never states this is a read-only operation, how results are ordered, or what happens when more than 50 rows match (silent truncation vs error).

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 with no filler, front-loading the resource and result set before the matching rule. Appropriately sized for a two-parameter tool, though the trailing 'up to 50' phrasing is slightly ambiguous.

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 must stand alone, and it does describe the return unit (rows) and cap. It omits ordering, whether all columns are searched across multiple datasets, and behavior on empty results, which leaves gaps for an agent composing a query workflow.

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 adds case-insensitivity for the query and clarifies that the 50 cap relates to the limit parameter, partially compensating. It still doesn't explain the default when `limit` is omitted or whether 50 is a default or a ceiling.

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 Contractor Lead Quotes dataset) with scoping detail — matches on cell content, case-insensitive. It does not name any sibling (e.g. dataset_top, dataset_row, dataset_compare) to distinguish itself, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no mention of alternatives, despite four closely related sibling tools (dataset_top, dataset_row, dataset_compare, dataset_stats) that an agent must choose between. Usage is only implied by the word '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, and it does disclose real behavioral traits: currency and comma grouping are normalized, and non-numeric rows are excluded but counted. It says nothing about permissions, behavior on an all-non-numeric column, or the response shape, which is a gap 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 returned metrics. The parenthetical earns its place by adding normalization and exclusion semantics, though the sentence packs a lot into a single clause chain.

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 or annotations, so the description usefully enumerates the returned values and the edge-case handling, which is what an agent needs to interpret results. It remains incomplete only on parameter format and any value-shape caveats.

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 single parameter 'column' has 0% schema description coverage, so the description must compensate. It does constrain the domain to numeric columns of one named dataset, but it gives no guidance on expected naming, case sensitivity, or how to discover valid column names (a sibling, dataset_columns, appears to exist for that).

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 metrics returned (count, min, max, mean, median, sum) and the exact resource (a numeric column of the Contractor Lead Quotes dataset), so the purpose is unambiguous. It does not differentiate itself from siblings such as dataset_top or dataset_compare, which keeps it below 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?

There is no statement of when to use this tool versus dataset_top, dataset_compare, or dataset_search, nor any preconditions. The phrase 'numeric column' implicitly narrows applicability, but the agent must infer the rest.

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 dataset scope (Contractor Lead Quotes) and that ranking is numeric, which is useful. However, it omits the 50-row cap, tie-breaking behavior, and what happens if the column is non-numeric or missing.

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 operation front-loaded and no filler. Slightly compressed punctuation, but nothing 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 read-only ranking tool with no output schema and no annotations, the description covers the core intent and the numeric-column constraint but leaves the limit cap and edge-case behavior unstated. Adequate but with clear 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 only 33% (only 'ascending' is documented), so the description must compensate. It adds the key constraint that 'column' must be numeric, which the schema does not state, but it says nothing about the 'limit' parameter or its 1-50 range.

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 clear operation (return the highest/lowest rows) on a specific resource (the Contractor Lead Quotes dataset) ranked by a numeric column. The 'which is the most/least X' phrasing pins the intent well. It does not explicitly contrast with siblings like dataset_row or dataset_search, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'which is the most/least X' framing implies when the tool is useful (ranking / extreme-value questions), but there is no explicit when-to-use, when-not-to-use, or named alternative such as dataset_row for a single row or dataset_stats for aggregates. Usage 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.

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

With no annotations provided, the description carries the burden and discloses important behavioral context: the enquiry is free, nothing is purchased or ordered, and no quote is guaranteed. It also says the tool returns who receives details, the consent wording, and confirmation behavior, though it stops short of explicitly declaring read-only status or auth needs.

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 concise and front-loads the key usage instruction with "Read first." It efficiently covers the main purpose and expectations without unnecessary filler.

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, no-output-schema describe tool with no annotations, the description provides enough context about what information is returned and what the enquiry does not involve. It could be slightly stronger by explicitly stating that it is purely informational/read-only, but it is largely complete for the tool's complexity.

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 has zero parameters, so there is no parameter semantics to document and the baseline is 4. The description's mentions of returned content are output-related rather than input parameter guidance.

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 that the tool plainly describes what submit_enquiry does and also returns consent-related details. It distinguishes the informational/read-first nature from the actual submission action, though it does not explicitly differentiate itself from other siblings such as enquiry_fields.

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" gives clear sequencing guidance: call this before submit_enquiry. It also clarifies expectations by stating that nothing is bought, ordered, paid, or guaranteed, but it does not name when not to use the tool or list alternative siblings.

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 does disclose the shape of the returned data and the downstream contract with submit_enquiry, which is genuine added context, but it never states that this is a read-only, side-effect-free inspection call with no rate limits or auth constraints.

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 of the payload is front-loaded and the integration hint follows as a single compact 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, the description steps in to enumerate the returned fields, which is exactly what is needed for a zero-parameter read tool. It is slightly thin on read-only semantics but otherwise gives an agent everything required to call it 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 tool takes no parameters, which is the baseline-4 case; there is nothing to document in the schema. The description usefully clarifies that returned field keys are the same keys expected by submit_enquiry, tying the zero-arg call to its purpose.

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 and enumerates exactly what it returns (key, label, type, required flag, help text, allowed options) for a named enquiry, which is far more concrete than the vague sibling name dataset_columns-type tools. It does not differentiate itself from enquiry_describe, the obvious adjacent sibling, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence implies the workflow ('Pass answers to submit_enquiry keyed by field key'), which tells the agent this is the discovery step before submitting. However there is no explicit statement of when to call this versus enquiry_describe, and no exclusion or prerequisite guidance.

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

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

With no annotations, the description carries the full burden and does so: it discloses validation behavior in step 1, the returned summary/consent line/token, the mutation in step 2, and the downstream consequence that an email link must be clicked before any provider sees the enquiry. It also defines exactly what consent asserts.

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 two-step structure is front-loaded and each sentence carries operational weight. The verbatim consent clause is somewhat long and partially duplicates the consent property description, but it is material to correct invocation, so the length is defensible.

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-step, no-output-schema, no-annotation tool, the description supplies everything an agent needs: the call sequence, required inputs per step, what step 1 returns, and the downstream email-confirmation requirement. Nothing essential 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 already 100%, so the baseline is 3, but the description adds meaning the schema does not: answers are keyed by field key sourced from enquiry_fields, and confirmation is a token produced by step 1 and used only in step 2. This step-dependent relationship between parameters is not derivable from the schema alone.

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 (an enquiry to Contractor Lead Quotes), and explicitly negates the two most likely misinterpretations: 'NOT a purchase, NOT a guaranteed quote.' It also names the related sibling enquiry_fields as the source of field keys, so an agent can place it without opening a 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?

Gives an explicit two-step procedure with clear triggers: step 1 when answers and consent=true are ready, step 2 only if the person agrees to the summary. The when-not (do not submit before approval) is stated as a hard condition rather than left to inference.

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