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 does state what the tool exposes (columns, numeric status, row count, provenance banner), but it does not explicitly state that the call is read-only or describe any other behavioral characteristics. For a no-parameter metadata tool this is acceptable but not fully 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 two sentences, directly front-loads the returned content, and includes the actionable 'Call this first' instruction. Every sentence adds value with 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?

The tool has no output schema and no annotations, so the description must cover what the call returns; it enumerates columns, numeric flags, row count, and provenance banner. This is sufficient for a schema-introspection call, though it could be slightly more precise about result format.

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 100% schema description coverage, so there is no parameter information needing explanation. Per the rubric, this warrants a baseline of 4.

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 (PaywallCompass dataset) and the information returned (columns, numeric flags, row count, provenance banner), and instructs to call it first to learn the schema. However, it lacks a direct verb such as 'returns' or 'lists,' and does not explicitly differentiate it from sibling dataset tools beyond the 'first' guidance.

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 'Call this first to learn the schema' gives explicit usage context and positions it as the entry-point tool before other dataset operations. It does not mention when not to use it or name alternatives, so it falls short of full exclusion 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, the description is responsible for disclosing behavioral traits. It does explain the selection logic and ordering, but it does not explicitly state whether the operation is read-only or whether it has any side effects, though the wording implies a pure query.

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, tightly written sentence that packs the selection rule, ordering rule, and intended use case without extraneous 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?

Given only two parameters and no output schema, the description provides enough context for an agent to understand what rows are returned and why. It could be slightly stronger by explicitly describing the output layout implied by 'side by side', but it is not critically 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?

The schema provides only names and types, so the description adds meaning by explaining that 'column' is a dataset column and 'values' are the values to match, with 'any of' semantics and order preservation. It does not cover edge cases such as matching behavior, but it gives the essential 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 clearly states that the tool retrieves rows from the PaywallCompass dataset by matching a column against a set of given values, and the title adds the 'compare rows side by side' intent. This distinguishes it from general search or single-row retrieval 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 explicitly scopes its use to 'X vs Y' questions and notes that results are returned in the order of the supplied values, giving an agent clear guidance on when to invoke it. It does not mention alternative sibling tools, but the use case is specific enough.

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 states what information is returned (source, date, licence, citation) but does not explicitly confirm read-only behavior, mention error conditions (e.g., if provenance is unavailable), or note any side effects. The description is accurate but not deeply transparent about behavioral edge cases.

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 redundancy. The first sentence lists the returned fields (source, date, licence, citation) and the second provides the use case. The title is short and informative. Every word 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 parameterless tool with no output schema, the description adequately covers what the agent needs to know: what fields will be returned and why to use the tool. It does not address edge cases like missing provenance data, but given the low complexity, 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 schema has zero parameters, so the baseline of 4 applies. The description does not need to explain any parameters since none exist, and it does not attempt to invent parameter semantics. This is appropriate for a parameterless tool.

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 provides provenance information (source, date computed, licence, citation) for the PayoffCompass dataset. The title 'Where this data comes from, and how to cite it' reinforces the purpose, and it is easily distinguished from sibling tools that query data values (dataset_search, dataset_stats, dataset_top) versus this metadata/provenance tool.

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 an explicit use case: 'Read this to attribute a figure correctly.' This implies when to use the tool (when citation/provenance is needed) and implicitly contrasts with sibling data-query tools. It does not explicitly name alternatives or state when not to use it, but the guidance is sufficient for the tool's simplicity.

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 must carry the full burden. It discloses case-insensitive matching but says nothing about read-only behavior, return format, multiple row handling, or error conditions. For a lookup tool, some behavioral context is expected.

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. It is appropriately concise and front-loaded with the essential information about the tool's 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?

The description is minimal and leaves critical gaps: no usage guidance, no parameter details, and no output specification. While the tool is simple, the lack of any guidance beyond the core action makes it incomplete for an agent to use 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 0%, and the description adds no explanation of the 'column' and 'value' parameters. It does not specify valid column names, value formats, or case-handling nuances beyond the single mention. The agent gains no additional meaning from the 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 returns rows from a specific dataset where a column matches a value exactly, with case-insensitivity. This is a specific verb-resource combination that differentiates it from dataset_search, though it does not explicitly name the alternative.

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 use this tool versus dataset_search or other siblings. The description does not mention scenarios, limitations, or when exact match is preferred over fuzzy search.

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 does disclose case-insensitive matching and a 50-row limit, which are useful behavioral traits. However, it does not state read-only behavior, ordering, or what happens when no rows match.

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. It front-loads the result type and key constraints (case-insensitivity, limit), making it easy to scan.

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 with no output schema, the description covers the core search semantics and constraint. But it omits usage context and expected response shape, which would help an agent interpret results or decide when to fall back to another sibling 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?

Schema coverage is only 50% (query is described, limit is not). The description compensates by explaining that matching is on any cell and case-insensitive, and 'up to 50' clarifies the limit parameter's purpose. Still, the limit's role as a result count control is only 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 states a specific action and resource: it returns rows of the PaywallCompass dataset whose cells contain the query, case-insensitively, up to 50. This is specific enough to distinguish it from siblings like dataset_row or dataset_stats, though it does not explicitly name the alternative.

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 is given on when to use this tool versus siblings such as dataset_row, dataset_stats, or dataset_top. The only usage cue comes from the tool name and title, not from 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?

Since annotations are absent, the description carries the burden of disclosing behavior. It transparently states that non-numeric rows are excluded and counted, and that grouping commas and currency are handled. This provides useful insight beyond the basic function.

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 all necessary information without fluff. It is front-loaded with the main purpose and then adds relevant caveats.

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 with one parameter and no output schema. The description explains what the tool does and the data quirks it handles. It does not explicitly state the return format, but that is not required for this level of complexity, making the description complete enough.

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 only defines a string parameter with minLength, providing no semantic meaning. The description compensates by specifying that the column must be numeric, which is essential context. It could go further by explaining allowed formats or examples, but it adds clear 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 clearly states that the tool computes count, min, max, mean, median, and sum for a numeric column of a specific dataset. This is a precise verb and resource, and it distinguishes the tool from siblings 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?

The description provides context about when to use the tool: for summary statistics on a numeric column. It also notes handling of commas and currency and that non-numeric rows are excluded, giving the user a clear sense of applicable situations. It does not explicitly mention alternatives, but the context is sufficient for a typical use case.

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 of behavioral disclosure. It only says rows are selected by numeric column and direction, but says nothing about what the result contains, what happens when limit or ascending are omitted, tie behavior, or error cases.

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 well-structured sentence with the core operation front-loaded and a natural-language usage cue attached. It is lean and avoids repetition, though its brevity contributes to the missing detail noted in other dimensions.

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 and no output schema, the description should explain defaults, limit behavior, and expected result form. It only delivers the core ordering concept and leaves the agent to infer important calling details and sibling-tool trade-offs.

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 adds useful meaning by specifying that 'column' must be numeric and by framing direction with 'highest (or lowest)', which maps to the ascending parameter. However, the 'limit' parameter is not explained, and with only 33% schema description coverage, the description only partially compensates for the schema's gaps.

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 the highest or lowest rows of the PaywallCompass dataset based on a numeric column, which is specific enough to identify its core function. It implicitly distinguishes itself from siblings like dataset_search and dataset_stats, but 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 quoted question 'which is the most/least X' implies the intended use case for top-N or bottom-N ranking questions. However, there is no explicit guidance on when not to use this tool or which alternative sibling tool to choose instead.

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 does it well: it states the tool is free, involves no purchase or payment, offers no guaranteed quote, and returns who receives details, consent wording, and confirmation behavior. This gives an agent a complete behavioral picture.

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 compact and front-loaded with 'Read first.' The middle sentence is slightly emphatic but not wasteful, making the overall structure efficient and 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?

For a zero-parameter informational tool with no output schema, the description sufficiently covers what the agent will learn and why it matters. It does not specify an output format, but for a plain-language explanatory tool this is an acceptable 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 tool has zero parameters and an empty schema, so there is no parameter meaning to add. The baseline score of 4 applies because no parameter documentation 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's purpose: it explains what submit_enquiry does on PaywallCompass, explicitly distinguishing it from a purchase or guaranteed quote. This immediately differentiates it from submit_enquiry and other siblings.

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 opening 'Read first' is an explicit instruction to consult this tool before acting on submit_enquiry, providing clear usage context. It does not explicitly compare with alternatives like enquiry_fields, but the intended use is well implied.

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 mention whether the tool is read-only, whether it has side effects, or any permissions or rate limits. The burden of transparency falls entirely on the description, which fails to address these aspects.

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, succinct sentence that lists the returned attributes and adds a practical note about supplying answers. No redundant or overly verbose wording is present.

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 are no parameters and no output schema, the description provides a complete picture of what the tool returns. It also gives the caller actionable context (how to pass answers), though it leaves minor ambiguity about whether this is a global form definition or enquiry-specific, which is not fully resolved.

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%, so the baseline is 3. The description adds no parameter-specific semantics since none exist, but it does provide context by noting how the returned field keys should be used with submit_enquiry, which slightly aids the caller.

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 every field of the PaywallCompass enquiry, enumerating the exact attributes (key, label, type, required, help text, allowed options). This unambiguously distinguishes it from siblings like enquiry_describe and submit_enquiry.

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 the tool is for retrieving field definitions, but it does not specify when to use this tool versus alternatives such as enquiry_describe. The cross-reference to submit_enquiry gives some context, but no explicit usage guidance is 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?

With no annotations provided, the description carries the full transparency burden and does well: it explains validation, the two-step confirmation mechanism, email delivery, and that providers only see the enquiry after the link is clicked. It also includes the exact consent statement the user must agree to.

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 organized into clear step 1/step 2 instructions and every sentence contributes to explaining the consent flow. The repeated consent text is necessary for legal clarity, and the warning that this is not a purchase is concise and valuable.

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 description provides enough context for an agent to execute the entire two-step flow successfully, including what responses to expect, when to proceed, and what happens after submission. It is complete given the absence of an output schema.

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 describes all three parameters, but the description adds useful context: answers should be keyed by fields from enquiry_fields, and the confirmation token comes from step 1 after approval. This improves the schema's basic descriptions without being redundant.

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 submits an enquiry to human providers and distinguishes it from a purchase or guaranteed quote. It also differentiates this from sibling tools like enquiry_fields by describing the submission flow.

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 explicit step-by-step usage instructions: first call with answers and consent=true to get a summary/token, then call again with the confirmation token only after the person approves. It also specifies when not to use it, such as for purchases.

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