site

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

With no annotations, the description carries the burden of behavioral disclosure. It states what information the tool provides but does not explicitly say it is read-only or non-mutating. The directive 'Call this first' strongly implies safe introspection, but the lack of an explicit safety statement prevents a higher score.

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 in which every phrase earns its place: the first lists the returned content, the second gives the call sequence. It is front-loaded with the most important information and contains no 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 tool with no output schema, the description adequately names the key returned components (columns, numeric flags, row count, provenance banner) and when to call it. It does not describe the exact response format, but that is a minor gap for such a simple metadata tool.

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, and schema coverage is 100%, so there are no parameter semantics the description needs to explain. Per the baseline rule for zero-parameter tools, a 4 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 identifies the resource (Termslane dataset) and the specific outputs: columns, numeric flags, row count, and provenance banner. It lacks an explicit verb like 'returns' or 'lists', which keeps it from a 5, but the content is unmistakable and distinct from sibling tools like dataset_search 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 positional guidance, making it clear this is the entry-point tool for schema discovery. It does not mention when not to use it or name alternatives, but for a zero-parameter metadata tool the guidance is sufficient.

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 reveals two important behaviors beyond the schema: rows are selected by matching any of the given values (OR semantics), and rows are returned in the order given in the values array. It omits output format and limits, but the core behavior is well exposed.

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 that front-loads the operation and selection semantics, then adds the use-case clause. Every word contributes; there is no redundancy or 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 simple two-parameter read tool with no output schema and no annotations, the description covers purpose, selection semantics, ordering, and typical usage. It does not describe the exact output format or edge cases, but the simplicity of the tool makes this 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 description coverage is 0%, so the description must explain the parameters. It does: 'column' is the field to match, and 'values' are the set of allowed matching values whose order determines row order. This goes beyond the bare schema by relating the two parameters to the 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 states a specific operation and resource: it returns rows of the Termslane dataset filtered by column membership, with order preserved. The phrase 'for "X vs Y" questions' clarifies its niche and distinguishes it from abstract sibling tools like dataset_search 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 scopes usage to 'X vs Y' comparison questions, which tells an agent when to prefer this tool. It does not name sibling alternatives or explicitly state when not to use it, but the context is clear enough for 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?

With no annotations, the description carries the full burden of behavioral disclosure. It clearly lists what information is returned and implies a read-only operation, but it does not explicitly state that it has no side effects or what happens if provenance data is unavailable. This is acceptable for a trivial zero-parameter tool but not fully self-sufficient.

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 carry all essential information, front-loading the content fields and ending with the actionable use case. There is no filler, redundancy, or unnecessary detail.

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, read-only metadata lookup with no output schema, the description is complete: it states the data source, the fields returned (source, date, licence, citation), and the use case. Nothing else is required for an agent 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 tool has zero parameters, so the description does not need to explain inputs. The baseline of 4 applies, and the description adds useful context about the returned provenance fields, which is the only semantics an agent needs.

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 resource (the Termslane dataset) and the exact content provided (source, computation date, licence, citation), plus the intended purpose ('attribute a figure correctly'). This makes it self-evidently distinct from siblings like dataset_row or dataset_stats, which return data values rather than provenance metadata.

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 a clear when-to-use instruction: read this when you need to attribute a figure correctly. It does not explicitly name alternatives or exclusions, but no sibling tool covers provenance metadata, so the guidance is unambiguous and sufficient for this 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 provided, the description carries the full burden of behavioral disclosure. It usefully reveals the case-insensitive exact-match behavior and states that rows are returned, but it does not describe no-match behavior, output format, pagination, or error conditions.

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, front-loaded sentence with no filler. Every element contributes to understanding the tool's core behavior.

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 is mostly sufficient, but with no output schema and no annotations it leaves gaps around expected return shape and edge-case behavior. Sibling routing guidance is also absent, so an agent has to infer when this tool is the right choice.

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 provides no descriptions for the two parameters, so the description must compensate. It does so by explaining that 'column' is a dataset column and 'value' is the exact value to match, including the case-insensitive comparison nuance. This gives an agent enough meaning to construct valid inputs.

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 names the operation (lookup/filter rows), the resource (Termslane dataset), and the exact matching semantics (column equals value, case-insensitive). It also differentiates itself from sibling tools like dataset_search by emphasizing exact rather than fuzzy 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 title and description imply the tool is for exact-key lookups, but there is no explicit statement about when to use it versus dataset_search or other siblings. No exclusions or alternative guidance are provided, leaving the usage context 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, the description carries the full behavioral burden. It does disclose important behavior: case-insensitive matching and a 50-row maximum. However, it does not mention whether the tool is read-only, what the default limit is when omitted, or what the returned rows look 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?

A single sentence with no filler. The core result is front-loaded, and every clause adds useful information about matching behavior or result limits.

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 provides the essential behavior an agent needs to call it: what is searched, how matching works, and the row cap. Minor gaps remain around the default limit and the exact shape of returned rows, but these are not critical for invocation.

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 50% because the limit parameter lacks a description. The description compensates by clarifying that the query is matched case-insensitively in any cell and that results are capped at 50, adding meaning beyond the schema's bare constraints.

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 verb and resource: it returns rows of the Termslane dataset matching a query in any cell. It also adds the key scoping details—case-insensitive matching and a 50-row cap—which distinguish it from sibling tools like dataset_stats 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?

The intended use is implied: use this tool when you need rows whose cells contain a given text. However, it does not explicitly say when to prefer it over sibling tools or when not to use it, so the agent must infer the decision from the sibling names alone.

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. It does add useful behavior details: grouping commas and currency are handled, and non-numeric rows are excluded and counted. However, it leaves ambiguity about the output structure, error handling for missing columns, and precise behavior for empty inputs.

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 the core functionality front-loaded and the edge-case handling in a parenthetical. Every phrase earns its place with no fluff or redundancy.

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 low complexity (one parameter, no output schema, no annotations), the description covers the main operation and two important behaviors. However, it does not specify the return format, which is arguably needed when there is no output schema, nor does it address failure scenarios like a nonexistent column.

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% and the schema only defines 'column' as a non-empty string. The description compensates somewhat by clarifying that the parameter refers to a numeric column in the Termslane dataset, but it does not explicitly state the expected input format or how column names map to the parameter.

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 resource (numeric column of the Termslane dataset) and the specific statistics computed (count, min, max, mean, median, sum). It implicitly distinguishes itself from siblings like dataset_row and dataset_top by offering aggregate statistics. It lacks an explicit verb like 'computes', which keeps it from a 5, but the meaning 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?

There is no guidance on when to choose this tool over alternatives or any prerequisites (e.g., column must exist, must be numeric). The description only states what the tool does, leaving the agent to infer suitability from the tool name and sibling 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 full burden. It mentions highest/lowest ordering but does not disclose default limit, tie-breaking, handling of missing/non-numeric values, whether it is read-only, or what result shape to expect.

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 filler, and the key ranking behavior is front-loaded. It could be phrased more smoothly, but it earns its place without redundancy.

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 no output schema and no annotations, the description leaves essential context missing: what rows look like, default limit, what dataset is targeted, and how it relates to dataset_row or dataset_stats. An agent would need to infer too much.

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 has a description). The description adds that column must be numeric and implies the ascending parameter, but limit is left entirely undocumented in both schema and description.

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 ranks rows by a numeric column and returns the highest/lowest, which distinguishes it from siblings like dataset_search or dataset_stats. The phrasing is slightly awkward but the core action and resource are identifiable.

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 is given about when to choose this tool over dataset_search, dataset_stats, or dataset_row. The phrase "which is the most/least X" implies a ranking use case, but there is no direct comparison or exclusion.

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