site

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

No annotations exist, so the description carries the full burden. It implies a read-only metadata query by describing returned metadata and no side effects, but never explicitly states that it is non-mutating, that it takes no arguments, or that it is cheap to call.

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, front-loaded with the returned content and closed with the calling instruction. Every clause earns its place, 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?

With no output schema, the description usefully enumerates the returned fields so the agent can anticipate the payload. It is largely complete for a zero-parameter introspection tool, with only the explicit read-only/no-side-effect guarantee 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, which sets the baseline at 4. There is nothing further for the description to document beyond confirming no input is required, which the empty schema already conveys.

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 concrete return contents (column list, numeric flags, row count, provenance banner) for a specific dataset, so an agent knows exactly what this returns. It only weakly differentiates from the sibling dataset_provenance, whose scope the 'provenance banner' phrase partially overlaps.

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, actionable ordering instruction for discovery. It does not name alternative tools or state when not to use it, so it stops short of full routing 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 fully carries the behavioral burden. It does add useful semantics beyond the schema: matching is 'any of' the values (OR semantics) and results preserve the given order. It is silent on error behavior for unmatched values, output shape, and any limits beyond the schema's maxItems.

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 dense sentence with no wasted words, and the dataset is front-loaded. But the sentence is grammatically awkward ('whose column is any of the given values'), which slows parsing for an agent scanning many tools.

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 2-parameter, no-annotation, no-output-schema tool, the description covers the filtering and ordering contract but not the return shape or failure modes. It is adequate to invoke the tool, but leaves an agent guessing about output and edge cases.

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

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

Schema coverage is 0%, so the description must compensate. It maps 'column' and 'values' plausibly and clarifies that matching is any-of and order-preserving, which is more than the schema says. It does not explain the column format (name vs index), matching strictness, or the 2-10 value constraint.

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 and states the exact retrieval semantics: rows whose column matches any given value, returned in the given order. That is specific enough to distinguish it from a generic search, though the phrasing is a noun fragment rather than a clear verb+resource statement and the 'compare side by side' behavior implied by the title is never explained.

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

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

'for "X vs Y" questions' gives a rough trigger condition, which is useful routing signal. However, no alternative sibling (dataset_search, dataset_row, dataset_top) is mentioned, and there is no guidance on when this is the wrong tool versus those.

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 discloses the kind of information returned and frames the call as a read, but says nothing about permissions, rate limits, or the shape of the response. For a trivial metadata read the burden is low, so this is adequate rather than rich.

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 tight sentences: the first front-loads the returned fields, the second states the use case. Every clause earns its place with no 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?

With no parameters and no output schema, the description is nearly self-sufficient — it lists the fields a caller will receive and the reason to call it. Only minor detail about return structure is absent, which is acceptable for this complexity.

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, which is the baseline-4 case. There are no parameter semantics to clarify, and the description correctly does not invent any.

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 resource (the Tide Times Compare dataset) and enumerates exactly what it returns — source, computed date, licence, citation. This clearly distinguishes it from siblings like dataset_stats, dataset_columns, and dataset_search, which surface data rather than 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?

'Read this to attribute a figure correctly' gives a concrete condition for invoking the tool. It does not name explicit alternatives or exclusion cases, but for a zero-parameter metadata lookup the selecting condition is unambiguous.

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 case-insensitive exact-match rule, but not whether multiple rows can be returned (the plural 'rows' only hints at it), what happens when the column does not exist, result limits, ordering, or permissions.

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 well-formed sentence that front-loads the resource and states the matching condition. No redundant or filler text, though the phrasing 'The rows of the ... dataset where' is slightly indirect.

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 is the only source of behavioral information, yet it omits return shape, multiplicity, ordering, and error handling. For a lookup tool with two undocumented parameters, this leaves significant gaps.

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 clarify that one parameter is a column and the other a value, and that the comparison is exact and case-insensitive, but it adds no detail on valid column names, value formats, or error behavior for unknown columns.

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 concrete operation on a concrete resource: exact-match row lookup against the Tide Times Compare dataset, with the matching rule (column equals value, case-insensitive) spelled out. It implies but does not name its sibling alternative dataset_search, so it is clear but not fully differentiated from 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 phrase 'equals a value exactly (case-insensitive)' implicitly tells the agent this is for exact lookups rather than fuzzy retrieval, which suggests when to prefer it over dataset_search. However, there is no explicit when-to-use statement, no exclusions, and no named alternative.

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

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

With no annotations, the description must carry the full behavioral burden. It usefully discloses case-insensitivity and the 50-row cap (implying result truncation), but says nothing about permissions, pagination beyond the cap, or ordering of results.

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 zero filler; matching scope, case behavior, and result cap are all stated economically.

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 read-only search with no output schema, the description tells the agent what is returned only in the abstract ('rows'). It never describes the shape/fields of a returned row, which is a gap given no output schema exists.

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, limit is not but its 1-50 bounds are constrained. The description reinforces the cap ('up to 50') and adds case-insensitivity for query, but gives no guidance on what the limit means in practice (ordering/tie-breaking).

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?

Clear verb (search) and resource (rows of the Tide Times Compare dataset) with a specific matching rule: cells containing the query, case-insensitive. It distinguishes itself from dataset_row/dataset_top implicitly via substring matching, but never names a sibling, so an agent must infer differentiation.

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 by the contains-match semantics: use it to find rows matching text. No explicit when-to-use versus dataset_top, dataset_row, or dataset_compare, and no exclusions or prerequisites are 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?

With no annotations, the description carries the full disclosure burden. It does add genuinely useful behavioral context — grouping commas and currency are normalized, and non-numeric rows are excluded but still counted — which is more than most definitions offer. It stops short of describing missing-value handling, error behavior for non-numeric columns, or return shape.

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 sentence, front-loaded with the returned metrics followed by the data-handling caveats. The parenthetical is dense but every clause carries information, and there is no filler or restatement of the tool name.

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 one-parameter tool with no output schema, the description effectively substitutes by enumerating the returned statistics, and it flags the numeric-only constraint and exclusion behavior. The main remaining gap is that an agent gets no hint about valid column identifiers or what happens when no numeric rows exist.

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 parameter 'column' has 0% schema description coverage, so the description must compensate. Saying the tool operates on 'a numeric column' implies the argument is a column name and is expected to hold numeric data, which adds real meaning beyond the bare string type, though it does not say how columns are referenced or whether names are case-sensitive.

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 Tide Times Compare dataset) and enumerates the specific outputs (count, min, max, mean, median, sum), so the tool's function is unambiguous. It does not, however, distinguish itself from siblings like dataset_top or dataset_compare, leaving routing 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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The only implicit signal is that the column must be numeric, which an agent could infer from the outputs listed, but nothing tells the agent when this beats dataset_top or dataset_row.

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 does not disclose how many rows are returned, whether ties are handled, what happens for non-numeric columns, or the output shape — significant gaps 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, front-loaded sentence that states the purpose before the clarifying example. The em-dash parenthetical is mildly redundant but adds a useful framing, so it is efficient overall.

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 should do more to explain return size, tie-breaking, and ordering mechanics. It covers the core intent and dataset but leaves practical invocation details unaddressed.

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 low (33% — only 'ascending' is documented in the schema). The description mentions 'numeric column' and 'highest (or lowest)', loosely mapping to column and ascending, but says nothing about the limit parameter's range (1-50) or column-name format, so it does not compensate for the coverage gap.

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 gives a specific verb and resource: it ranks/returns the highest (or lowest) rows of the named dataset by a numeric column, illustrated with the 'most/least X' use case. An agent can tell it apart from dataset_row or dataset_stats conceptually, though no sibling is named 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?

The 'which is the most/least X' framing implies the intended question type, giving implicit usage context. However, there is no explicit when-to-use vs when-not guidance and no mention of the alternative sibling tools (e.g. dataset_stats or dataset_search) for related ranking/aggregation needs.

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 substance: nothing is bought, ordered or paid, no quote is guaranteed, it is free, and it describes who receives the details and the consent wording. It does not clarify whether this descriptor tool itself has any side effects or auth requirements.

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 imperative "Read first" and reasonably compact, but the middle sentences are run-on and spend most of their budget explaining the sibling tool rather than this one.

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 must cover the return value, and it does list recipients, consent wording, and confirmation mechanics. Given the trivial empty input schema and read-only nature, this is largely adequate, though it could more clearly separate its own output from submit_enquiry's behavior.

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; baseline for a no-parameter tool is 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?

It signals a read-only descriptor ("Read first") and explains that it documents what submit_enquiry does, plus returns consent/recipient/confirmation details. The framing leans heavily on describing the sibling submit_enquiry rather than this tool itself, which slightly blurs what enquiry_describe returns versus what it explains.

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 an explicit ordering instruction implying it should be consulted before submit_enquiry, and the title clarifies this is not a purchase or guaranteed quote. It stops short of naming alternatives or listing when-not-to-use conditions.

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 contract in detail (key, label, type, required, help text, options), which is the main behavior an agent needs since no output schema exists. It is silent on ordering, caching, or how the options list behaves when empty, so it is strong but not exhaustive.

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. The return contents are front-loaded and the actionable usage tip is placed last where it is most useful, and 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 parameterless lookup with no annotations and no output schema, the description substitutes for the missing output schema by enumerating the returned fields, which is exactly what is needed. The only residual gap is the absence of any hint about field ordering or whether the set is static versus dataset-dependent.

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 are zero parameters, which sets the baseline at 4. The description introduces no parameter-level semantics because none are needed, and it does not confuse the reader with phantom 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 states precisely what the tool returns: 'Every field of the Tide Times Compare enquiry: key, label, type, whether required, help text and the allowed options where there are any.' This is a specific resource with an enumerated return shape, letting an agent distinguish it from sibling tools like dataset_columns. It does not, however, explicitly contrast itself with the nearby enquiry_describe or 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 second sentence gives a concrete downstream workflow hint: 'Pass answers to submit_enquiry keyed by field key,' which links this lookup to its consumer. But it never says when to call this versus enquiry_describe, nor states any precondition for invoking it, so the usage guidance is implied rather than explicit.

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 does so: it discloses the side effect (enquiry submitted, email sent with a verification link), the prerequisite for provider visibility, the return payload of step 1 (summary, consent line, token), and the exact consent meaning with quoted wording. This is well beyond a restatement of the name.

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 'NOT a purchase' disambiguation, then the two steps in order – every sentence contributes. Slightly dense as a single paragraph, and the consent sentence is quoted verbatim both here and in the schema, a minor redundancy for a reader consulting both.

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 mutation with no output schema and no annotations, the description supplies everything an agent needs: what each call returns, what to show the user, what token to carry forward, and the consent gate. Nothing required to invoke it correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: answers are keyed by field key drawn from enquiry_fields (a cross-tool contract), consent=true is defined by the quoted agreement text, and confirmation is explicitly the token returned by step 1. It stops short of describing answer value formats or typing 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?

States a specific verb (submits) and resource (an enquiry to Tide Times Compare) and immediately negates the two most likely confusions – 'NOT a purchase, NOT a guaranteed quote'. The two-step structure is named outright, so an agent can distinguish it from the read-only dataset_* and enquiry_* siblings without opening a 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?

Gives explicit conditional routing: step 1 with answers plus consent=true to validate; step 2 only if the person agrees, adding the confirmation token from step 1. It also states the gating condition (person must click the emailed link before any provider sees it), so the agent knows exactly when each call is appropriate and when the flow must stop.

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