site

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 exact contents of the response and frames the tool as a read-only schema-learning operation, which strongly implies no mutation. It does not discuss auth or rate limits, but for a zero-parameter metadata introspection tool these are low-risk and the description covers the essential behavior.

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

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

Two brief sentences carry all necessary information. The output contents are front-loaded, and the usage guidance is appended without waste. The first sentence is a grammatical fragment, but it remains highly scannable and concise.

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 zero parameters and no output schema, the description sufficiently explains what the tool returns and when to call it. It does not detail return formatting, but the tool's purpose is to reveal the schema itself, and sibling tools cover other access patterns. An agent has enough 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?

The input schema has zero parameters, so the description correctly includes no parameter information. The baseline of 4 applies for tools with no parameters, and the description adds nothing that could confuse an agent.

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 tool's output: columns, numeric flags, row count, and provenance banner of the Curtilo dataset. It lacks an explicit action verb like 'returns' or 'lists', but the fragment is easily understood, and 'Call this first to learn the schema' reinforces the purpose. It differentiates itself from siblings by being the schema-introspection first step.

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' explicitly tells the agent when to invoke this tool, positioning it as the initial step before any other dataset operation. It does not name alternative tools or exclusions, but the temporal instruction provides clear usage context.

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 burden of behavior. It discloses the core filtering rule and that output follows the order of the given values, which is useful. However, it does not state whether matches are exact, whether full rows are returned, or what happens with no matches.

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 fragment that front-loads the core behavior and appends the use case. 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 two-parameter tool this is mostly sufficient, and the schema supplies parameter shapes. The absence of an output schema and annotations leaves some ambiguity about the return format and matching behavior, so it is not fully complete.

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 explain both parameters. It does clarify that 'column' is the field to match and 'values' are the candidate values whose order controls output. This adds meaningful semantics beyond the bare schema.

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 resource (Curtilo dataset rows), the selection mechanism (rows whose column matches any of the given values), and the ordering constraint. It is clear enough to distinguish from sibling tools like dataset_search, though it does not name 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?

"For X vs Y questions" explicitly states the intended use case: comparing specific values in a column side by side. It does not list exclusions or alternative tools, but the context 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?

No annotations are provided, so the description carries the full burden for behavioral disclosure. It clearly explains what information the tool will return and frames it as a read-only lookup. Although it does not explicitly state 'read-only' or 'no side effects', the zero-parameter nature and descriptive content make the behavior transparent enough.

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 two concise sentences with no filler. It front-loads the core content and ends with the practical instruction on when to read it; every sentence 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 zero-parameter metadata lookup with no output schema, the description fully covers what an agent needs: the returned categories and the intended use case. 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?

The tool has zero parameters, so there is nothing to document. The baseline for a parameterless tool is 4, and no additional semantic explanation 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 states exactly what the tool returns: source, computed date, licence, and citation for the Curtilo dataset. It also connects the purpose to a concrete use case ('attribute a figure correctly'), and the title reinforces the scope. This clearly distinguishes it from the data-manipulation sibling tools.

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 clear usage context: read this when attribution of a figure is needed. It does not explicitly mention alternatives, but with zero parameters and a distinct provenance purpose, the intended use is unambiguous relative to the 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?

No annotations exist, so the description bears full responsibility for behavioral disclosure. It adds useful behavior: matching is exact and case-insensitive. However, it does not state whether the operation is read-only, how results are returned, or what happens on no/multiple matches.

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 sentence with no redundant phrases. It front-loads the resource ('rows of the Curtilo dataset') then the condition. Every word contributes.

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

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

For a simple two-parameter lookup, the description covers the core operation, but lacks an output schema and behavioral details like return shape or error behavior. It also does not clarify which dataset's columns are valid or if multiple rows can be returned. These gaps make it minimally viable rather than complete.

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%, so the description must compensate. It connects the two parameters by explaining a column is compared to a value, and that the comparison is exact and case-insensitive. It does not specify whether the value or column strings require specific formatting, but the simple schema already provides the string type.

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 the tool returns rows from the Curtilo dataset where a column matches a value exactly, and notes case-insensitivity. This clearly differs from a fuzzy search tool like dataset_search, though it does not explicitly name it. No explicit verb is present, but the title supplies 'Look a row up'.

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 this tool is for exact-match row lookups, but does not state when to prefer it over dataset_search or other siblings. There are no explicit exclusions or alternative tool mentions. The 'exactly (case-insensitive)' wording hints at the niche but leaves routing 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 provided, the description carries the behavioral disclosure burden. It discloses case-insensitive substring matching and a 50-row limit, which are important behavioral traits. It does not mention ordering or pagination, but for a simple read-only search tool these are minor gaps.

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 one tight, front-loaded sentence. Every word adds value, and there is 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?

The tool is simple, has only two parameters, and the description covers the core behavior and the main constraint (up to 50 rows). It does not describe ordering or default limit, but these are not critical for an agent to invoke 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?

Schema coverage is 50%: the query parameter already has a description, and the description reinforces it with 'cells contain the query' and adds case-insensitivity. The limit parameter is not described in the schema, and the description only repeats the 50 max already present in the schema, adding no meaningful new semantics.

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 exactly what the tool does: returns rows of the Curtilo dataset whose cells contain the query, and it adds specific behavior (case-insensitive matching, 50-row cap). This clearly distinguishes it from sibling tools like dataset_columns or dataset_stats, which serve different purposes.

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 context is implied: use this when you need dataset rows matching a text query. However, there is no explicit guidance about when not to use it or how it compares to siblings such as 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 provided, the description carries the full burden of behavioral disclosure. It usefully reveals that grouping commas and currency formats are handled and that non-numeric rows are excluded and counted, which adds genuine behavioral context beyond the tool name. It does not describe the output structure, but the metric list substantially covers expected 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 a single compact sentence that front-loads the computed statistics and appends only essential parsing behavior in parentheses. There is no redundancy or wasted wording.

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 one-parameter statistics tool with no annotations and no output schema, the description covers the input expectation, the dataset scope, and the returned metrics. It does not explicitly describe the response format or error behavior, but the enumerated statistics are enough for an agent to understand what the tool provides.

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 provides no description for the 'column' parameter, so the tool description must compensate. It does by clarifying that the column must be numeric and that formatted values such as commas and currency are accepted. It could add guidance on where valid column names come from, but the single-parameter case is mostly covered.

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 for a numeric column, enumerating exact metrics (count, min, max, mean, median, sum) and scoping it to the Curtilo dataset. This makes its purpose distinct from siblings like dataset_row, dataset_top, and dataset_columns without ambiguity.

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 intended use is implied: use this tool when you need numeric summary statistics for a column. However, it does not explicitly state when to prefer it over siblings such as dataset_top or dataset_row, nor does it provide exclusion criteria or alternative 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 must carry the behavioral disclosure burden. It does describe the core behavior—sorting rows by a numeric column and returning top or bottom rows—but it omits details like limit defaults, tie-breaking, handling of non-numeric values, or read-only guarantees.

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 front-loads the ranking purpose. Minor redundancy exists with the title ('numeric column' repeats), but the added 'most/least X' phrasing earns its place by clarifying the intended query.

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 ranking tool, the description conveys the essential operation and return type (rows). However, with no output schema and no annotations, important details such as the default limit value, behavior on non-numeric columns, and explicit read-only status are missing, leaving the agent to infer them.

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%, so the description needs to compensate. It adds important meaning by specifying that the column must be numeric and indicating the ascending/descending intent, but it does not explain the 'limit' parameter beyond what the schema's min/max bounds imply.

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 the highest or lowest rows by a numeric column, which is a specific ranking operation. It conveys the 'most/least X' use case and can be distinguished from sibling tools like dataset_search or dataset_stats, 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?

The phrase 'which is the most/least X' gives a clear implied use case for the tool. However, it does not explicitly say when to prefer this tool over siblings such as dataset_stats or dataset_row, and it offers no exclusions or alternative guidance.

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