site

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

With no annotations, the description carries the burden of disclosure. It transparently lists what the tool returns (columns, numeric flags, row count, provenance banner), which implies a read-only inspection operation. It does not explicitly state side effects, but none are indicated, and the nature of the tool suggests no destructive 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?

The description is concise, consisting of two short sentences. It packs essential information: what is returned (columns, numeric flags, row count, provenance) and when to call it (first). There is no redundant or extraneous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description adequately explains the output content and purpose. It mentions all key elements an agent would need to know: the dataset name, the type of information (columns, types, row count, provenance), and the recommended invocation order. This provides sufficient context for correct usage.

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, and the schema coverage is 100% with an empty properties object. Per the rubric, a baseline of 4 is appropriate since there are no parameters to describe. The description correctly implies that no input is required.

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 clearly states the tool's purpose: it returns the columns, numeric column indicators, row count, and provenance banner of the Retainvia dataset. It also explicitly says to call this first to learn the schema, which effectively distinguishes it from sibling tools that handle comparing, searching, or 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?

The description provides explicit usage guidance: 'Call this first to learn the schema.' This instructs the agent on when to invoke this tool relative to others, implying it is a prerequisite for understanding the dataset structure. No alternative tools are mentioned, but the prioritization is clear.

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?

The description mentions the ordering behavior ('in the order given') but does not explicitly state the operation is read-only or describe side effects. Since there are no annotations, the description carries full burden but lacks an explicit safety statement.

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

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

The description is a single, focused sentence that front-loads the core purpose and includes the key detail about ordering. There is no filler or redundant content.

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 filtered retrieval tool, the description covers the essential behavior. It does not specify the output format (e.g., which columns are returned) or error conditions, but given the tool's simplicity, this is a minor 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 description directly explains both parameters: 'column' is the attribute to filter on, and 'values' are the matching values. This adds meaningful semantics beyond the raw schema, clarifying the filtering and ordering behavior.

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 clearly states the tool returns rows from the Retainvia dataset that match any of the given values for a specified column, in the provided order. This distinguishes it from sibling tools like dataset_row (single row) and dataset_search (generic 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 description gives a use case ('for X vs Y questions') but does not explicitly name alternatives or explain when to choose this over dataset_search or dataset_top. Usage guidance is implied rather than explicit.

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 supplied, the description carries the behavioral disclosure burden. It discloses the returned content (source, date, licence, citation) and implies a read-only action through 'Read this'. For a zero-parameter provenance tool, this is adequate, although it doesn't explicitly state that no data is modified.

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, each earning its place: the first defines the scope and content, the second states the intended use. No filler or repetition.

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, parameterless provenance lookup, the description is complete: it names the dataset, the exact metadata fields, and the user scenario. No output schema exists, but the listed fields serve as sufficient expectations of the return value.

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 input schema is empty with zero parameters, so there are no parameter semantics to document. The baseline for no-parameter tools is 4, and the description adds no unnecessary parameter details.

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 clearly identifies the tool as providing provenance metadata for the Retainvia dataset: source, computed date, licence, and citation. The title reinforces this and the content distinguishes it from sibling tools that operate on columns, rows, stats, or comparisons.

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

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

The phrase 'Read this to attribute a figure correctly' gives a concrete when-to-use trigger: whenever attribution is needed. It does not name sibling alternatives or exclusions, but the described purpose is sufficiently distinct that no further routing is 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?

No annotations are provided, so the description carries the behavioral disclosure burden. It does reveal the non-obvious case-insensitive behavior, which is useful. But it does not state whether all matching rows or a single row are returned, what happens when no row matches, or what the response shape 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?

The key information is packed into one short sentence, and the important qualifier 'exactly (case-insensitive)' is included. The sentence is a noun phrase rather than a complete action statement, but the title supplies the verb, keeping the overall definition compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema and annotations, the agent is left to infer the return format, row cardinality, and no-match behavior. The basic lookup intent is clear, but the description is not fully actionable on its own.

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 add meaning to the two bare parameters. It successfully explains that 'column' is the field being matched and 'value' is the exact, case-insensitive comparison target. It does not list valid column names, but the two string parameters are otherwise self-explanatory.

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 a lookup operation on the Retainvia dataset and specifies a precise criterion: a column equals a value exactly and case-insensitively. It distinguishes itself from dataset_search through the 'exactly' qualifier, though it does not name the sibling explicitly and mixes 'a row' in the title with 'rows' in the description.

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 exact-match and case-insensitive phrasing implies this tool is for precise key lookups rather than fuzzy or partial search. However, the description never explicitly states when to prefer this tool over dataset_search or other siblings, nor does it give any 'when not to use' 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 provided, the description carries the burden of behavioral disclosure. It usefully reveals case-insensitive matching, substring containment across cells, and a 50-result cap, but it does not mention default limit behavior, sorting, empty-result behavior, or return structure.

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-structured sentence delivers the core behavior, matching mode, case sensitivity, and result cap without redundancy. Every phrase 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?

For a simple two-parameter search tool with no output schema, the description covers the essential invocation semantics: what is searched, how matching works, and the result ceiling. It could be more complete by stating the default limit and response shape, but the core contract is clear enough for an agent to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema documents query but not limit; the description adds meaningful semantics by explaining that the query is matched against cells case-insensitively and that results are capped at 50. This partially compensates for the 50% schema description coverage, though the explicit link to the limit parameter is implicit.

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 clearly states that the tool returns dataset rows matching a query, with case-insensitive cell containment and a 50-row cap. It is specific about the resource and behavior, though it does not explicitly distinguish itself from sibling tools like dataset_row or dataset_top.

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 about when to use this tool versus alternatives such as dataset_stats, dataset_row, or dataset_top. The intended usage is only implied by the word 'search' in the name and the contains-query semantics in the description.

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 behavioral disclosure burden. It goes beyond a simple summary by revealing that grouping commas and currency are parsed, and that non-numeric rows are excluded and counted. This is valuable transparency for a data-processing tool, though it omits details like error handling or empty-column 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?

A single, efficient sentence packs the core purpose, target dataset, computed statistics, and a key parsing behavior. There is no fluff or repetition; every element contributes to understanding the 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 tool with one parameter, no output schema, and no annotations, the description covers purpose, applicable data types, and an important data-cleaning characteristic. It is reasonably complete for the low complexity, though return format and error conditions are not described.

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 does clarify that the column must be numeric and mentions formatting handling, which adds meaning beyond the schema's bare 'string' type. However, it doesn't explain how to reference the column, whether exact names are required, or any edge cases beyond non-numeric rows.

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 clearly enumerates the statistics computed (count, min, max, mean, median, sum) and names the target resource (Retainvia dataset). It is distinguishable from siblings like dataset_search or dataset_top, though it lacks an explicit verb such as 'computes' or '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?

The description implies usage for numeric columns and signals that currency/grouping formats are handled, but it does not explicitly state when to prefer this tool over alternatives such as dataset_top or dataset_compare. No exclusions or alternative routing are provided.

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?

Describes the core behavior—returning top/bottom rows sorted by a numeric column—and references both ascending and descending directions. However, it does not disclose default limit behavior, tie handling, or null handling, and there are no annotations to fill the 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?

Extremely concise; one sentence plus an illustrative phrase, with no filler or redundant content.

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 or return-format description is provided, so an agent cannot know whether the result is a list of rows, row IDs, or field subsets. Limit defaults and edge-case behavior are also absent, making the tool underspecified for robust 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?

Only 'ascending' has an inline schema description; 'column' and 'limit' are not described in schema. The description adds that the column must be numeric and clarifies highest/lowest order, but leaves 'limit' semantics and default unspecified.

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?

Clearly identifies dataset_top as a ranking/selection tool for the highest or lowest rows by a numeric column, with the 'which is the most/least X' example reinforcing the intended use. It is distinct from sibling row/search/stats tools, though it does not explicitly name them.

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 explicit guidance on when to choose this tool over siblings like dataset_search or dataset_stats. The 'which is the most/least X' phrase implies ranking use, but alternatives are never mentioned.

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