site

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

With no annotations, the description carries the full burden, and it does disclose the return profile in detail (columns, numeric flags, row count, provenance banner) plus the fact that it is a cheap entry-point call that should precede others. It stops short of stating side-effect-freeness explicitly or any cost/latency expectations, which is a minor gap for a zero-parameter metadata tool.

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 sentences, no filler, and the imperative call-to-action is placed at the end where it reads as a directive. The first sentence is a dense list, but every item in it is return-value information rather than padding.

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?

There is no output schema, so the description has to describe the return shape itself, and it does so by enumerating the four things an agent gets back. Field names, types, and the exact provenance-banner format remain unspecified, but for an orientation/introspection call the description is sufficient to call 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 takes zero parameters, so there is nothing to document and the baseline of 4 applies. The description neither needs nor attempts to explain invocation arguments.

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 resource (the Equipment Rental Compare dataset) and enumerates exactly what is returned: columns, which are numeric, row count, and the provenance banner. That is a specific, verifiable purpose rather than a restatement of the name, though it does not explicitly differentiate itself from the sibling dataset_provenance despite both apparently touching provenance.

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 a clear ordering cue that implies when to use it relative to the other dataset_* tools. However, it states no when-not conditions and never names an alternative (e.g., dataset_stats or dataset_provenance) for agents who only need counts or provenance, leaving that inference to the caller.

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 disclosure burden. It does disclose one behavioral trait — result order follows the order of the given values — but says nothing about read-only nature, permissions, result size, or what the rows contain.

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 front-loaded with the returned resource, though it opens as a noun fragment rather than a verb-led statement, which slightly weakens scannability.

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?

With no output schema, no annotations, and 0% schema description coverage, the description leaves the agent guessing about return shape, ordering semantics of the output, and error behavior. For a two-parameter filtering tool this is under-specified.

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

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

Schema description coverage is 0%, so the description must compensate. The phrase 'whose column is any of the given values' does implicitly map 'column' to a column name and 'values' to match targets, which is useful, but it never mentions the 2-10 value constraint or formatting of values.

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 specific dataset (Equipment Rental Compare) and states the operation: return rows where a column matches any of the given values, preserving order. It distinguishes itself from dataset_row/dataset_search by framing the operation as comparison-oriented, though it never explicitly contrasts with those 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 trailing clause 'for "X vs Y" questions' gives a concrete usage cue, which is real guidance. However, there is no explicit when-not condition and no alternative tool named (e.g. dataset_search for single-value filtering), so the agent must infer 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?

No annotations are provided, so the description carries the burden, and it does disclose the content of the returned record (source, date, licence, citation). However, it never states that the call is read-only, side-effect free, or static per dataset, nor whether the citation is a fixed format — minor but real gaps for an unannotated tool.

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 sentences, no filler, with the returned content front-loaded ahead of the usage note. Every clause 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?

With no output schema, the description compensates by listing the fields returned, which is the key information an agent needs. It stops short of describing the citation's format or the response structure, but that is a small omission for a no-argument metadata getter.

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 takes zero parameters, so there is nothing to disambiguate and no risk of malformed invocation; the description correctly implies the dataset is fixed and no arguments are 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?

Names the specific resource (the Equipment Rental Compare dataset) and enumerates exactly what it returns: source, computed date, licence, citation. An agent can distinguish it from dataset_stats, dataset_columns and dataset_search, though it uses a noun phrase rather than an explicit verb.

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?

"Read this to attribute a figure correctly" gives one concrete use context, but there is no guidance on when not to use it and no named alternative among the nine sibling tools. Usage is implied rather than stated.

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 behavioral burden. It adds useful matching semantics (exact, case-insensitive), but says nothing about how many rows come back, ordering, result limits, or empty-match behavior for what is implicitly a read operation.

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 waste, front-loading the returned resource. It is efficient, though the relative clause makes the filter condition slightly harder to scan than a direct imperative.

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, the definition states what is returned at a high level but omits the return shape, cardinality, and any limits. Adequate but with clear gaps an agent would want before calling.

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

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

Schema description coverage is 0%, so the description must compensate; it maps 'a column' and 'a value' to the two required parameters, which is genuinely useful. However, it gives no column-name format, no guidance on reserved/pseudo columns, and no example values.

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?

Names a specific verb (returns rows) and resource (Equipment Rental Compare dataset) with the filter condition. It is distinguishable from dataset_search/dataset_stats in spirit, but it never names a sibling, so sibling differentiation is left to inference.

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 'equals a value exactly (case-insensitive)' phrasing implies this is for exact-key lookup rather than fuzzy/text search, but there is no explicit when-to-use statement and no mention of dataset_search as the alternative for non-exact matching.

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. It usefully discloses that matching is case-insensitive and that results are capped at 50, but says nothing about ordering, whether all columns are returned, or how to page beyond the cap.

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 front-loaded sentence with no filler; the resource and the matching constraint come first and nothing is redundant.

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?

There is no output schema and no annotations, so the description is the only source of behavior. It covers matching and the result cap but omits return shape (which fields per row), ordering, and sibling relationships, leaving the definition adequate but not 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 50%: 'query' is documented in the schema, while 'limit' is not. The description partially compensates by clarifying that matching is substring-over-any-cell and case-insensitive, and by restating the 50 cap, but it never explains how 'limit' interacts with that cap. Baseline 3 for partial coverage with marginal added meaning.

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?

It names the specific resource (rows of the 'Equipment Rental Compare' dataset) and the retrieval semantics (cells containing the query), so an agent can tell this apart from dataset_row or dataset_top by implication. It stops short of explicitly naming a sibling as the non-overlapping alternative, so it is clear rather than fully differentiated.

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 when-to-use statement, no prerequisites, and no mention of alternatives such as dataset_row (fetch a known row) or dataset_top (ranked rows). The usage context is only inferable from the description of what it returns, which is thin 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 carries the full burden, and it does disclose real behavior: commas and currency are normalized, and non-numeric rows are excluded and counted. It is silent on error behavior for a non-existent or non-numeric column, permission needs, and the exact shape of the returned counts.

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?

One dense sentence that front-loads the returned metrics and appends the data-cleaning caveats. Every clause earns its place, though the parenthetical caveats make it slightly heavy 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?

With no output schema, the description usefully enumerates the six returned metrics and explains non-numeric handling, which is the key edge case for a stats tool. Missing only the failure mode for an invalid column name.

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 single 'column' parameter has 0% schema description coverage, so the description must compensate. It does establish that the column belongs to the Equipment Rental Compare dataset and must be numeric, which adds real meaning, but it gives no naming convention, prefix, or example 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?

States a specific verb (summary statistics) and resource (a numeric column of the Equipment Rental Compare dataset), and enumerates the exact metrics returned. It does not, however, explicitly contrast itself with siblings like dataset_top or dataset_compare that also operate on 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?

Usage is implied: use it when you need aggregates for a numeric column. There is no explicit when-to-use/when-not or named alternative, so an agent must infer the boundary against dataset_top and dataset_compare on its own.

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 and largely fails it: it never states that results are capped at 50 rows, what the default limit is, whether ties are broken deterministically, or what the returned rows look like. The only disclosed trait, high-vs-low ordering, is already encoded in the ascending parameter.

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 compact sentence, front-loaded with the operation and scoped to the named dataset, with the parenthetical example adding an interpretive hook. Nothing is wasted, though the terseness comes at the cost of the missing operational 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 three-parameter tool with no annotations and no output schema, the description is minimally viable: it establishes purpose and the numeric-column constraint. It leaves the limit parameter's behavior and the shape of the result unexplained.

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 33% (only ascending is documented), so the description must compensate. It does clarify that the column must be numeric, which the bare schema does not say, but limit's default and 50-row ceiling remain undocumented in both places.

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?

Names a specific operation (return highest/lowest rows) on a specific resource (the Equipment Rental Compare dataset) keyed by a numeric column, and frames it as the answer to 'which is the most/least X'. It does not name or distinguish itself from any sibling such as dataset_search or dataset_stats, which are the likely alternatives for this kind of query.

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 'which is the most/least X' framing implies the use case (extremal lookup rather than full listing or aggregation), which is better than nothing. However it never states when to prefer this over dataset_stats, dataset_search, or dataset_row, nor any prerequisites or exclusions.

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 to lean on, the description carries meaningful behavioral context: nothing is bought, ordered or paid, no quote is guaranteed, and the call is free. It also previews the returned content (who receives details, consent wording, confirmation flow), which is valuable since there is no output schema. It stops short of 5 only because it doesn't discuss rate limits, freshness, or failure modes.

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 'Read first.' directive is front-loaded and each following sentence adds a distinct claim (no purchase, no guarantee, free, what is returned). It is slightly wordy and self-referential in restating what the tool 'states plainly,' but there is no filler that fails to inform.

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 explainer with no output schema and no annotations, the description supplies enough: it identifies the subject (submit_enquiry's behavior) and enumerates the returned material (recipients, consent wording, confirmation). An agent knows what it will get back, though it could be more explicit that this is a static documentation read rather than live data.

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 takes zero parameters, so there are no parameter semantics to explain and the baseline is 4. Nothing in the description misrepresents the argument surface, and no parameter-level detail is expected.

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 function: it 'states plainly what submit_enquiry does on Equipment Rental Compare,' making it clear this is an explanatory/read tool about the enquiry flow rather than the submission itself. It effectively distinguishes itself from the sibling submit_enquiry by framing itself as documentation rather than the action. The framing is slightly meta and the title describes content ('What you get: an ENQUIRY...') rather than the tool's own verb, which keeps it just short of a 5.

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?

'Read first.' gives a directional hint that this should be consumed before acting (presumably before submit_enquiry), but it never explicitly states when to call it versus alternatives like enquiry_fields or submit_enquiry. The routing intent is implied rather than spelled out, so it lands at minimum-viable 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 carries the full burden, and it does disclose the return contents and the zero-argument, purely descriptive nature of the call. It stops short of explicitly stating read-only/no-side-effect behavior or the exact response shape, but for a metadata lookup that is a minor omission.

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 sentences, zero filler, with the returned field list front-loaded and the actionable workflow tip second. Every clause carries information.

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?

There is no output schema, but the description compensates by enumerating the returned field attributes, and it links to the consuming tool submit_enquiry. It is complete enough for a zero-param metadata tool, though it could note ordering or whether options are conditionally present.

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 takes no parameters, so there is no parameter semantics to document; the baseline for a zero-parameter tool is 4. Nothing in the description misrepresents the (empty) input contract.

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 and enumerates exactly what each field contains (key, label, type, required, help text, options), which is far more than a restatement of the name. It does not explicitly differentiate itself from the sibling enquiry_describe, which is the one gap keeping it from a 5.

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 concrete downstream guidance: answers should be passed to submit_enquiry keyed by field key, which tells the agent how this tool fits into the workflow. It does not state when this tool should be preferred over enquiry_describe, so no exclusions or explicit 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 carries the full burden and does so richly: it discloses that step 1 validates and returns a summary/consent line/token, that the person must click an email link before providers see data, and spells out the exact consent wording. These are non-obvious behaviors an agent could not infer.

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?

Front-loads the critical distinction (NOT a purchase/quote) before the procedural detail. It is dense and long, but nearly every clause carries operational meaning; minor compression is possible but nothing is truly wasted.

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 stateful, two-call tool with nested answers, no output schema, and no annotations, the description supplies everything needed: step sequencing, return values, consent semantics, and the email-confirmation gate. An agent can execute both steps correctly from this text alone.

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 100%, so baseline is 3, but the description adds value beyond the schema by explaining the cross-parameter state machine — confirmation token only applies to step 2 after approval, and answers must be keyed by field key from enquiry_fields. It maps the consent boolean to explicit wording.

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?

States a specific verb+resource (submits an enquiry to human providers) and immediately disambiguates it from a purchase or guaranteed quote. It also distinguishes itself from read-only siblings like enquiry_fields and enquiry_describe, which merely describe or list fields rather than submit.

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?

Explicitly lays out the two-step protocol: step 1 with answers+consent=true to validate, step 2 with token only after the person agrees. The when-to-proceed condition is stated rather than inferred, and the alternative (not a purchase) is excluded.

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