site

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

No annotations are provided, so the description carries the full burden, and it does disclose the read-only nature of the operation by describing its inspection output (columns, row count, banner). It omits any statement about permissions or whether the banner reflects live configuration, but for a zero-parameter metadata read that is a minor gap.

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 returned content front-loaded and the imperative usage hint placed last, which is the right ordering for an entry-point tool. Slightly compressed phrasing ("the columns, which of them are numeric...") 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?

With no output schema, the description must convey return values, and it lists the four outputs an agent needs before calling the siblings. No safety caveat is required for a parameterless read, so the definition is essentially complete, with only the numeric-flag format left 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 no parameters, so there is nothing for the description to clarify; baseline 4 applies. No parameter-level detail is expected or missing here.

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 (the Stocktaka dataset) and enumerates exactly what it returns: column names, which are numeric, the row count, and the provenance banner. That is far more specific than the title, though it never explicitly contrasts itself with siblings like dataset_provenance or dataset_stats.

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 and implies the tool should precede the other dataset_* calls. It stops short of naming a non-overlapping alternative or stating exclusions, so it is clear context without full routing.

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 disclose result ordering ("in the order given"), which is a real trait, but says nothing about read-only scope, what happens when a value is absent from the column, or how the implicit Stocktaka dataset is selected.

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?

Single short fragment with no filler, so it is tight. But it is grammatically incomplete and front-loads the return shape rather than the action, making it slower to parse than a verb-first sentence would be.

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-required-parameter tool with zero schema coverage, no annotations, and no output schema, the description is too thin: it never states the dataset source assumptions, the 10-value cap, or error behavior on misses. An agent can guess but cannot be certain how to invoke 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?

Schema description coverage is 0%, so the description must compensate. It usefully clarifies that matching is any-of (IN semantics) on one column and that output follows input order — semantics the schema does not express. It still omits the value-count constraints (2-10), duplicates/invalid values, and whether 'column' is a header name or index.

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 concrete resource (rows of the Stocktaka dataset) and a concrete filter (column matches any of the given values), which tells an agent what it will get back. It does not explicitly contrast with the closest sibling (dataset_row, dataset_search), but the 'X vs Y' framing hints at its niche. The phrasing is a noun phrase rather than a verb-led statement, which weakens it slightly.

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?

"for 'X vs Y' questions" gives a usable when-to-use cue, which is the main thing separating this from the other dataset_* lookups. However, no alternative is named and no exclusion is given (e.g., when to prefer dataset_row for a single entity or dataset_search for substring matching).

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 discloses the returned content but says nothing about read-only safety, whether the values are static or recomputed, caching, or freshness guarantees. For a zero-parameter metadata lookup the risk is low, so the implicit read of static metadata is mostly self-evident, but the disclosure is 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?

Two tight sentences with no filler; the payload (what fields come back) is front-loaded and the usage cue follows it.

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 partially compensates by listing the fields a caller receives, which is the key information for an attribution task. It stops short of naming exact field names or return format, but nothing essential for invoking a zero-arg tool 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?

There are zero input parameters, so the baseline is 4; the description correctly adds no parameter guidance because none is needed.

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 returns — source, computation date, licence, and citation for the Stocktaka dataset — which is highly specific and clearly distinct from the data-oriented siblings (columns, row, stats, top). It lacks an explicit verb (e.g., 'get'/'return'), so it reads as a noun phrase rather than a stated action, but the resource and its contents are unambiguous.

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 situational trigger for calling the tool. No alternatives or exclusions are named, but given that no sibling provides provenance or citation data, there is no real ambiguity to resolve.

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 discloses the case-insensitive matching semantics, which is genuine behavioral context, but says nothing about whether multiple rows can be returned, result limits, pagination, or auth requirements.

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, stating the resource and filter condition immediately. It is appropriately sized, though its brevity is partly the source of the definitional gaps elsewhere.

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 tool with no annotations, no output schema, and 0% parameter coverage, the description should do much more. It omits cardinality (one row vs. many), result limits, error behavior for no-match cases, and any column/value format guidance.

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. It loosely maps 'column' and 'value' to their roles and adds the case-insensitive matching rule, but gives no guidance on column naming conventions (IDs vs. labels), value formatting, or whether the column name itself is case-sensitive.

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-equivalent (look up rows) and resource (rows of the Stocktaka dataset) with a precise filter predicate (column equals value exactly, case-insensitive). It implicitly distinguishes itself from siblings like dataset_search by specifying exact equality, but never names an alternative tool 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?

No when-to-use or when-not-to-use guidance is given; the agent must infer that this is for exact-match lookups rather than search or top-N retrieval. No prerequisites, alternatives, or routing hints are provided despite the presence of six 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 behavioral burden and does disclose useful traits: matching is case-insensitive and results are capped at 50. It does not state that this is a read-only operation, describe result ordering, or explain what happens with zero matches; the cap is also already implied by the schema's limit maximum.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with no waste; the resource is front-loaded and the matching rule and result cap follow in order of usefulness.

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 should say more about the return shape (what fields a row contains), any ordering, and whether it is read-only. For a simple search tool this is minimally adequate but leaves real 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 50% (the limit parameter has no description), so the description must compensate, and it does: 'whose cells contain the query (case-insensitive)' explains the matching semantics of query, and 'up to 50' clarifies limit's effect as a result-count cap. It still doesn't explain limit's default or lower bound.

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 operation: return rows of the Stocktaka dataset whose cells contain the query. The matching rule (substring across any cell, case-insensitive) tells an agent what kind of result set to expect. It doesn't explicitly contrast itself with siblings like dataset_row or dataset_columns, so differentiation is only implicit.

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 guidance on when to prefer this over dataset_row, dataset_top, dataset_compare, or dataset_columns. Usage as a free-text cell search is inferable, but there are no stated conditions, prerequisites, 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?

With no annotations, the description carries the full disclosure burden, and it does add real behavioral context: grouping commas and currency symbols are parsed, and non-numeric rows are excluded but counted. It stops short of describing the response shape, where the excluded-row count is surfaced, or what happens if the named column does not exist or is non-numeric.

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 front-loads the exact outputs and then packs clarifying preprocessing behavior into one parenthetical. No filler text, though the parenthetical could have been split for 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?

For a one-parameter, no-annotation, no-output-schema tool, the description covers what is computed and how messy input is handled. The main remaining gap is that it says non-numeric rows are 'counted' without explaining where that count appears in the result.

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% - the schema only declares 'column' as a non-empty string. The description compensates partially by implying the column must be numeric and must belong to the Stocktaka dataset, and by explaining that non-numeric values are tolerated rather than erroring. It still does not clarify valid column naming, case sensitivity, or whether the column name is validated against the dataset.

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 computation (count, min, max, mean, median, sum) against a specific resource (a numeric column of the Stocktaka dataset), so an agent immediately knows what it produces. It does not explicitly differentiate itself from siblings like dataset_top or dataset_compare, but the operation is distinct enough to be inferred.

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 alternatives, nor any prerequisites or exclusions. The agent must infer that it is for numeric aggregation rather than, say, dataset_top or dataset_compare, based purely on the task wording.

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 conveys only ordering direction and adds nothing about return shape, tie-breaking, defaults, what happens when the requested column is non-numeric, or permission/rate considerations — a significant gap for a query 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 with the resource and scope stated first and zero filler. The trailing example phrasing is compact and useful, so little 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 annotations, no output schema, three parameters at 33% description coverage, and no stated defaults beyond a one-word schema hint, the description is too thin for an agent to call this confidently. It should at least cover limit behavior and what is returned.

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 the ascending flag). The description adds that the column must be numeric and implies the highest/lowest semantics, which partially maps to 'column' and 'ascending', but it says nothing about 'limit' — its range, default, or cap of 50 — leaving a third parameter undocumented in both places.

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 named resource (the Stocktaka dataset) scoped to a numeric column. An agent can distinguish this ranking tool from siblings like dataset_stats or dataset_rows, though the description never names an alternative 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 quoted user-phrasing “which is the most/least X” implicitly signals the intended use case (superlative/ranking questions), which is better than nothing. However, it gives no guidance on when to prefer this over dataset_stats or dataset_search, and states no prerequisites or exclusions.

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