site

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

With no annotations, the description carries the burden, and it does disclose the information it returns. It does not state that the operation is read-only or mention any side effects, retention, or caveats, but for a schema-inspection tool this is an acceptable baseline.

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 no redundancy. The output list is front-loaded and the usage directive is concise and direct; every word contributes value.

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 tool, the description provides the essential context: what data it exposes, for which dataset, and the recommended invocation order. The only minor gap is not explaining what a 'provenance banner' is, but that is a domain term an agent can resolve from the dataset context.

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 parameters, so the baseline is 4. The description adds no param-specific detail because none is needed; the empty input schema is already fully 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 names the exact resource (Weekrota dataset) and the specific outputs (columns, numeric flags, row count, provenance banner), so an agent knows precisely what the tool returns. The 'Call this first to learn the schema' cue also differentiates it from the sibling tools as the intended entry point.

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

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

It gives an explicit, actionable usage instruction: call this first to learn the schema. However, it does not enumerate when not to use it or name alternatives, so it falls short of the full 'when/when-not/alternatives' bar.

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, and the description does not disclose any side effects, return format, or error behavior. It only states what rows are returned without specifying the output structure or any potential mutations (though it is likely a read-only operation). The lack of explicit behavioral details reduces transparency.

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, concise sentence that communicates the core functionality without superfluous detail. It is well-structured and directly addresses the tool's purpose, making it easy to parse.

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 simplicity of the tool, the description provides enough context for a user to understand what it does. It does not mention output format, pagination, or limitations (e.g., max values), but these are implied by the schema. The description is adequate for its complexity, though slightly more detail on the result structure would improve completeness.

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 explains that 'column' is the field to match and 'values' are the acceptable values (any of). It also mentions the order is preserved. This adds meaning beyond the schema, which only defines types and constraints. The description covers both parameters effectively, though it could be slightly more explicit about the column's role.

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 retrieves rows from the Weekrota dataset based on a column matching any of the given values, in the order provided. The title 'Compare rows side by side' gives a general sense, but the description clarifies the specific function. It is distinguishable from sibling tools like dataset_row (single row) and dataset_search (likely broader 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 includes the phrase 'for "X vs Y" questions,' which provides clear guidance on when to use this tool—specifically when comparing rows based on a column's values. While it does not explicitly contrast with sibling tools, the usage hint is sufficient to guide appropriate selection.

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

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

No annotations are provided, so the description carries the burden. It clearly lists the four pieces of information returned and implies a read-only operation ('Read this'). It doesn't describe return format or error cases, but for a simple metadata tool this is adequate.

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 concise sentences, front-loaded with the core content (source, date, licence, citation). Zero wasted words and the use case is clearly stated.

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 tool returning static metadata, the description covers the essential content. It doesn't describe the exact return structure, but given the simplicity, an agent can reasonably infer the output from the listed items.

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 the baseline is 4. The description adds no parameter-specific detail, but 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 clearly states the tool provides provenance information: source, computation date, licence, and citation for the Weekrota dataset. This is a specific verb+resource (retrieve provenance for dataset) and clearly distinct from sibling tools like dataset_columns 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?

The description explicitly says 'Read this to attribute a figure correctly,' giving a clear when-to-use scenario. It doesn't mention alternatives or exclusions, but the purpose is so specific that ambiguity is minimal.

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 of behavioral disclosure. It adds the key detail of case-insensitivity and exactness, which are useful. However, it does not disclose what happens when no match is found, when multiple rows match, or if the column is invalid, nor does it state the return format. These are gaps given the lack of annotations.

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 with no redundant wording. It front-loads the core behavior (exact match) and adds the case-insensitivity nuance. It is appropriately sized for a simple tool, though it could briefly mention alternatives without becoming verbose.

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 tool's simplicity (2 params, no output schema) and the existence of sibling tools like dataset_search, the description provides adequate core information but lacks explicit differentiation. It does not guide the agent on when to pick this tool over dataset_search, and it omits potential edge-case behaviors, leaving some context incomplete.

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%, and the description does not explicitly describe the 'column' and 'value' parameters beyond implying them in the phrase 'where a column equals a value'. It adds no specifics about allowed values, formats, or the relationship between parameters, failing to compensate for the absent schema documentation.

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: looking up rows where a column equals a value exactly. It specifies the resource (Weekrota dataset) and the operation (exact match, case-insensitive). It distinguishes from likely fuzzy search tools by emphasizing 'exactly', though it doesn't name siblings 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 description implies when to use this tool (when an exact, case-insensitive match is needed) but provides no explicit guidance on when not to use it or which sibling tool to choose instead. It does not mention dataset_search or other alternatives, leaving the decision to the agent's 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, the description discloses key behaviors: case-insensitive matching, search scope (any cell), and a result cap of 50. It doesn't mention ordering or error behavior, but the core behavior is clear.

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 sentence, front-loaded with purpose, no wasted words.

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

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

For a simple search tool with no output schema, the description covers the essential: what is searched, case-insensitivity, and limit. Minor gaps like ordering or no-result behavior are acceptable.

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 covers 50% (query has description). The tool description adds context for the limit (cap of 50) but doesn't add syntax details. The query parameter is already described in schema, so the description adds marginal value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action (search rows) on a specific resource (Weekrota dataset) with a clear filter (cells contain query) and a cap (50). It is unambiguous and distinguishes 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?

No guidance on when to use this vs siblings. The description implies a search use case but doesn't name alternatives or exclusions, so an agent has to infer when to choose this over dataset_row or dataset_top.

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 transparency burden. It discloses specific behaviors: handling grouping commas and currency, and excluding non-numeric rows. This gives useful insight into edge-case handling, though it does not mention errors, performance, or exact output format.

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, compact sentence that packs essential information without fluff. It is well-structured and front-loads the main function.

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 sufficiently explains what the tool returns (the six statistics) and how it handles data quirks. It lacks details about the exact output container (e.g., JSON object) but that is not strictly required without an output schema. Overall it is complete enough for an agent to understand the tool's purpose and behavior.

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

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

The schema already fully describes the single 'column' parameter (type string, minLength 1). The description adds no extra meaning about the parameter itself—the note about commas/currency applies to the data values, not the parameter. Since schema coverage is 100%, baseline 3 is appropriate.

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 computes summary statistics (count, min, max, mean, median, sum) for a numeric column, which is specific and distinguishes it from sibling tools like dataset_row or dataset_search. The verb is implied rather than explicit, but the intent is 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?

The description mentions the Weekrota dataset but provides no guidance on when to use this tool versus alternatives. It does not explain when statistics are needed versus retrieving raw rows or columns, so usage context is limited.

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. It does not explicitly state that the operation is read-only, does not mention the default ordering (highest first), or clarify the role of the limit parameter. The behavior is only partially transparent.

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

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

The description is a single concise sentence with a clarifying example. It contains no redundant information and is well-structured for quick comprehension.

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?

The tool is simple, but the description omits important context such as the return format, the effect of the limit parameter, and error behavior for non-numeric columns. It is adequate for basic usage but not fully complete given the lack of an output schema and annotations.

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 one of three parameters (ascending) has a schema description, yielding 33% coverage. The description mentions a 'numeric column' but does not explain the 'limit' parameter or the default value for 'ascending'. Since schema coverage is low and the description does not compensate, parameter semantics are under-specified.

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 title and description clearly state the tool's purpose: ranking rows of the Weekrota dataset by a numeric column to find highest or lowest values. The example phrase 'which is the most/least X' reinforces the intended use case, and the verb 'Rank' is specific.

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 top/bottom N queries and provides a natural-language example, but it does not explicitly state when to prefer this tool over siblings like dataset_stats or dataset_search, nor does it mention any prerequisites (e.g., the column must be numeric).

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