site

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

No annotations are supplied, so the description carries the full burden. It discloses the return contents, which is valuable given there is no output schema, but it never states that this is a safe read-only call, whether the dataset is fixed or can be mutated, or anything about cost/pagination.

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, with the payload of what is returned stated up front and the usage cue ('call this first') placed at the end where it belongs. Slightly list-like in the first sentence but no wasted prose.

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 and no annotations, the description must explain the return shape, and it does enumerate all four returned elements. It is adequate for a trivial zero-argument lookup; only the read-only/safety framing 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 takes zero parameters, so per the rubric the baseline is 4. There is nothing for the description to disambiguate, and it adds no misleading parameter guidance.

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 (PropFirmPicker dataset) and enumerates exactly what is returned: columns, numeric flags, row count, provenance banner. It is distinguishable from dataset_row / dataset_search / dataset_stats by being the schema-lookup call. It stops short of a 5 because the signposting is content-listing rather than a crisp verb+resource framing.

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 ordering guidance, which is genuine when-to-use direction. It does not, however, exclude or contrast with siblings that overlap, notably dataset_provenance, whose subject matter (the provenance banner) is also claimed here.

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 and no output schema, the description carries the full burden. It does disclose one behavioral trait — results preserve the order of the given values — but says nothing about return shape, the 10-value cap, dataset scoping/permissions, or whether all dataset columns are searchable. That leaves most behavioral traits undisclosed for a zero-annotation 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?

A single compact sentence that front-loads the dataset and the selection rule with no filler. It loses a point only for being a dangling fragment (no verb) that reads awkwardly rather than as a crisp instruction.

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 (two required params, no nesting, no output schema), and the description covers the core selection logic well enough to call it. It still leaves gaps around what a comparison actually returns ('rows side by side' is only in the title) and the value-count limits, so it is adequate 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 description coverage is 0%, so the description must compensate. It does convey the key relationship between the two parameters: 'column is any of the given values' tells the agent the match is OR-semantics over the values array, which the bare schema does not. It still omits the minItems=2/maxItems=10 bounds and any notion of how the 'order given' maps to the values array.

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 a specific resource (rows of the PropFirmPicker dataset) and the selection rule (column matches any of the given values, returned in given order), which goes beyond a tautology. However it is a verbless fragment that never states what the tool actually does as an action, and it does not contrast itself with siblings like dataset_search or dataset_row beyond the vague 'X vs Y' framing.

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 an implied usage context, telling the agent this is for comparison-style lookups. There is no when-not guidance, no prerequisites, and no named alternative (e.g. dataset_search or dataset_row) to route between, so the guidance stays at the implied level.

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

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

No annotations are provided, so the description carries the full burden. It discloses the returned content (source, computed date, licence, citation) and implies a pure read with no inputs and no side effects, which is the key behavioral fact here. It stops short of stating anything about freshness, limits, or reuse terms of the licence itself.

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

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

Two short sentences, with the returned fields front-loaded and the use case second. No filler, no repetition of the title, and nothing that could be cut.

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?

This is a low-complexity, parameterless metadata lookup with no annotations and no output schema, so the description must stand in for the return shape — and it does by enumerating the four fields. It is adequate for correct invocation, with only minor room to say how the citation should be formatted.

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 no parameter meaning to convey; the baseline for a parameterless tool applies. Nothing in the description misleads about 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 names the resource (the PropFirmPicker dataset's provenance) and enumerates exactly what it yields: source, computation date, licence, and citation. That distinguishes it from siblings like dataset_columns, dataset_stats, and dataset_search, which return data rather than metadata. It lacks a verb, so it reads as a content label rather than a stated action.

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 a concrete triggering condition: use it when a figure needs citing or attributing. It does not name alternatives or state when not to use it, but the intended context is clear enough for an agent to select it.

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 only adds case-insensitive exact matching and omits return format, result limits, sorting, error behavior, authentication needs, and whether multiple rows can 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?

A single sentence with no filler, front-loading the resource and matching rule. It is appropriately sized for a simple lookup tool.

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 annotations, no output schema, and 0% parameter description coverage, the description is incomplete. It lacks usage context, valid column discovery, result behavior, and error handling, so an agent cannot confidently invoke it beyond the simplest call.

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 identifies the column/value relationship and case-insensitive exact matching, but does not explain valid column names, allowed value types, or how to discover columns, leaving the two required parameters poorly specified.

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

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

States a specific resource (rows of the PropFirmPicker dataset) and precise matching condition (column equals value exactly, case-insensitive). It distinguishes itself from sibling dataset_search by emphasizing exact equality, though it does not name alternatives.

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 when-to-use guidance, alternatives, or exclusions. The exact-match condition implies a lookup scenario, but the agent is not told when to prefer dataset_search for broader queries or dataset_columns to discover valid column names.

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 disclose useful traits: matching is case-insensitive, it scans any cell, and results are capped at 50. It omits ordering of results, behavior when there are zero matches or when more than 50 rows match, and whether the cap truncates silently.

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, front-loading the resource and the matching rule before the result cap. 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?

For a two-parameter search tool with no output schema, the description says results are rows but not which columns/fields are returned, how results are ordered, or how truncation at 50 behaves. Adequate but leaves callers guessing about the response.

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 already has a schema description ('text to look for in any cell') but limit has none. The description adds the case-insensitive matching rule for query, which is real value beyond the schema, while 'up to 50' merely restates the schema's maximum.

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 (search) and resource (rows of the PropFirmPicker dataset) and narrows the scope to cells containing the query. It is clear enough to distinguish from dataset_columns, dataset_row, or dataset_top, though it never names those siblings explicitly.

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

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

There is no explicit guidance on when to choose this tool over dataset_row, dataset_top, or dataset_compare. The substring-over-all-cells semantics imply a use case, but the agent is left to infer routing decisions from 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, the description carries the full burden, and it does disclose two genuinely useful behaviors: grouping commas and currency symbols are handled, and non-numeric rows are excluded but counted. It is silent on permissions, error behavior for a fully non-numeric or unknown column, and the response shape, so the disclosure is real but incomplete.

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 the metric list front-loaded and the data-cleaning caveats tucked into a parenthetical. Efficient, though the parenthetical makes it slightly run-on.

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?

No output schema exists, but the description enumerates the returned metrics, which is what an agent needs. Combined with the one-parameter schema, it is nearly complete, missing only error/edge-case behavior for invalid or non-numeric columns.

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

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

There is one required parameter, 'column', with 0% schema description coverage, so the description must compensate. It implies the column must be numeric and implicitly identifies it by name, but adds no detail on name matching, case sensitivity, or behavior for a non-numeric column.

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

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

The description names the exact resource (a numeric column of the PropFirmPicker dataset) and enumerates the six statistics returned, so an agent knows precisely what this computes. It is clear and specific, though it never explicitly contrasts itself with siblings like dataset_columns 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?

No when-to-use guidance and no alternatives are named. The agent must infer from the metric list that this is the tool for aggregate statistics on a numeric column, with no exclusions or routing advice versus the eight sibling dataset_* 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 are supplied, so the description carries the full behavioral burden. It conveys the ranking operation but says nothing about read-only safety, how ties or non-numeric columns are handled, default/limit behavior, or what is returned. This is a significant gap for a tool with zero annotation coverage.

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 efficient sentence that front-loads the core operation and appends a short use-case gloss. No wasted text, though it is terse enough to leave some needed detail out.

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?

No output schema exists, yet the description does not describe the returned rows or their shape, and the 'limit' parameter's default behavior is unstated. It covers the essential column/ascending semantics but is only minimally complete for correct 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 33% (only 'ascending' is documented). The description usefully adds that the column must be numeric and that the direction is highest-or-lowest, which the schema does not state. However, the 'limit' parameter (max 50, no default shown) is never explained, leaving part of the gap uncompensated.

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 and resource: returning the highest/lowest rows of the PropFirmPicker dataset ranked by a numeric column. The "which is the most/least X" framing makes the intent concrete. It does not explicitly differentiate itself from siblings like dataset_row or dataset_stats, which keeps it 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?

The parenthetical "which is the most/least X" implies a use case (finding extremes), but there is no explicit when-to-use, when-not-to-use, or named alternative among siblings (e.g., dataset_row for a single record, dataset_stats for aggregates). Usage is only 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 provided, so the description carries the full burden, and it discharges it well: nothing is bought, ordered or paid, no quote is guaranteed, it is free, and it discloses the return content (recipients, consent wording, confirmation mechanism). It does not cover auth/permission needs or any rate limits, keeping it short of a 5.

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?

Three tight sentences with the actionable directive ('Read first') front-loaded and no filler. Slightly awkward that the middle sentence is about a sibling tool rather than this one, which costs a point.

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 and no annotations, the description must stand in for both, and it does describe the substantive return fields (recipients, consent wording, confirmation). No parameter or safety gaps exist for a zero-arg read tool, so this is close to 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly implies a no-input lookup rather than a parameterized query.

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 name and description together convey that this tool returns explanatory content about the enquiry flow, and the final sentence ('Also returns who receives the details, the consent wording, and how the person confirms') does state what the tool itself emits. However, the bulk of the text describes submit_enquiry's behavior rather than this tool's, so an agent must infer that enquiry_describe is the documentation/read-first companion rather than a distinct action.

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' implies a sequencing rule relative to the enquiry flow, which is genuine guidance. But no alternatives are named, and it never states explicitly whether this must precede submit_enquiry or is optional background reading.

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 shape of the returned data (field key, label, type, required flag, help text, allowed options). It does not state that the call is read-only/has no side effects, but for a no-parameter enumeration tool the disclosure of return content is the meaningful part and is well covered.

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, front-loaded with what the tool returns and followed by the one integration fact that matters. No filler, no restatement of the title.

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 has to explain the payload, which it does by enumerating the field attributes. Minor gaps remain (no explicit statement of read-only behavior, no note on ordering or pagination), but for a zero-parameter listing tool the agent has what it needs.

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 per the rubric the baseline is 4. The description adds the only relevant semantics that could exist here, namely that 'field key' is the identifier used to key answers into submit_enquiry.

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 precisely ('Every field of the PropFirmPicker enquiry') and enumerates the properties returned (key, label, type, required, help text, options), so an agent knows exactly what this tool yields. The verb is only implied ('every field of...') and it does not explicitly contrast itself with the sibling enquiry_describe, which keeps it 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?

It gives one concrete forward reference — 'Pass answers to submit_enquiry keyed by field key' — which tells the agent how the output feeds the next call. However it never states when to call this versus enquiry_describe, nor any precondition, so usage is only 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?

With no annotations, the description carries the full burden and does so: it discloses the validate-first-then-confirm two-call flow, that Step 1 returns a summary, consent line and token, that the enquiry is not visible to providers until the person clicks an email link, and what consent literally means. It also explicitly negates the purchase/quote expectations an agent might otherwise assume.

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-loaded with the negation and the two-step structure, and every clause is operative (validation, token, email gate, consent wording). It is dense and slightly run-on with nested quoting of the consent line, but no sentence is 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?

Three parameters including a nested object, no output schema, and the description compensates by describing the Step 1 return payload and the end-to-end flow through email verification. An agent has everything needed to sequence the two calls and set consent 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 100%, so the baseline is 3; the description goes further by explaining that answers are keyed by field key from enquiry_fields (pointing at the sibling that supplies valid keys) and that the confirmation token must accompany the same answers from Step 1. It stops short of type or validation-rule detail, which the schema carries.

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 and resource ("Submits an enquiry to PropFirmPicker") and immediately disambiguates with "NOT a purchase, NOT a guaranteed quote". Together with the title's "two steps" framing, an agent can distinguish this from sibling enquiry_fields/enquiry_describe without opening any schema.

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 prescribes exactly when to call: Step 1 with answers + consent=true for validation, Step 2 only after the person agrees, resubmitting the same answers plus the confirmation token. It also tells the agent to show the summary and consent line to the person before proceeding, which is the decision gate an alternate tool would not have.

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