site

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 implies a read-only introspection call and discloses what is returned, but says nothing about output size, cost, or any constraints on repeated calls. Adequate but not 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 short sentences with zero waste, and the return contents are front-loaded ahead of the usage instruction. The phrasing 'The columns, which of them are numeric...' is slightly awkward as a sentence fragment but remains efficient.

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 parameters, the description correctly enumerates the return payload, giving the agent enough to know what it will receive. Nothing essential is missing for a simple no-argument introspection tool.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-level gaps exist to compensate for.

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 (the Send A Parcel Compare dataset) and enumerates exactly what it returns: columns, numeric flags, row count, and provenance banner. It is clearly an introspection/shape tool and distinguishable from siblings like dataset_search or dataset_stats, though the 'provenance banner' element slightly overlaps with dataset_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?

Gives explicit ordering guidance: 'Call this first to learn the schema,' which tells the agent when to reach for this tool before the other dataset_* tools. It does not name a specific alternative or state when-not to use it, so it falls short of a full 5.

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 behavioral burden and mostly fails. It does disclose one real trait — result ordering follows the order of the supplied values — but says nothing about read-only safety, what happens when a value has no matching row, or duplicate/multi-row behavior.

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?

It is a single short sentence with no padding, which is good. However, the phrasing "whose column is any of the given values" is genuinely confusing — it blurs column name with cell value — so brevity comes at the cost of clarity.

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 this is thin: no annotations, no output schema, zero parameter descriptions, and an ambiguous core sentence. An agent can guess the call shape but cannot confidently predict return structure or edge-case 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?

Schema description coverage is 0%, so the description must compensate, and it partially does: it clarifies that 'column' identifies a column and 'values' are matched against it, with order preserved. It never states the 2-item minimum / 10-item maximum or that values are strings, so the compensation is incomplete.

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 identifies the resource (rows of the Send A Parcel Compare dataset) and the filter semantics (column matching any of the given values, returned in the given order), which separates it somewhat from dataset_row and dataset_search. But it is a sentence fragment with no explicit verb to 'compare', so the operation's purpose is only inferred, not stated.

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 an implied usage context, which is more than nothing but far short of explicit guidance. No alternatives are named and no exclusion conditions are given, even though siblings dataset_row, dataset_search, and dataset_top compete for similar lookups.

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 it does disclose the content returned (source/date/licence/citation). However, it says nothing about whether the metadata is static or cached, when it was last refreshed, or any doubt about the value beyond 'attribute a figure correctly'. For a zero-param metadata read the risk is low, so a middle score is fair.

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, no filler, with the returned fields front-loaded before the usage instruction. 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?

There is no output schema, so the description must convey the return shape, and it does by enumerating the four returned fields. Combined with zero parameters and no annotations, this is nearly complete; only the absence of any note on freshness or stability of the metadata keeps it from a 5.

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. No parameter guidance is needed and none is misleadingly offered.

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 it returns — source, computation date, licence and citation for the 'Send A Parcel Compare' dataset — so an agent knows exactly what payload to expect. It implicitly separates itself from the data-access siblings (dataset_columns, dataset_stats, dataset_row), which all return data rather than metadata, though it never names that contrast 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?

'Read this to attribute a figure correctly' gives one concrete trigger for calling the tool, which is more than implied usage. But there is no guidance on when not to call it, no mention of prerequisites, and no routing to or away from any sibling tool.

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 but does add real behavioral detail: the match is exact, case-insensitive, and returns 'the rows' (plural, so multiple matches are possible). It is silent on row limits, ordering, and empty-result behavior, which matters for a lookup that can match many rows.

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 with no filler. It front-loads the returned resource but starts with 'The rows of...' rather than an action verb, which is slightly indirect for a tool definition. 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?

For a two-parameter read lookup with no output schema, the description need not explain return format. However, it leaves out operational details an agent needs: caps on returned rows, multi-match behavior, and how column names are validated. Adequate but with clear 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% and neither parameter is documented in the schema, so the description must compensate. It does map both params to their roles ('a column equals a value') and adds that the value comparison is case-insensitive, but it omits how to discover valid column names (e.g. via dataset_columns) or accepted value forms.

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 concrete retrieval action (returning rows) against a named resource (the Send A Parcel Compare dataset) with the match condition spelled out. The 'exactly (case-insensitive)' phrasing implicitly contrasts it with the search-style sibling, though it never names one. Clear but not explicitly differentiated from dataset_search 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?

There is no explicit when-to-use or when-not-to-use statement, and no alternatives are named. The word 'exactly' implies this is the tool for exact-key lookups rather than fuzzy search, which is only implied guidance. An agent must infer the boundary with dataset_search 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 burden and does disclose useful traits: case-insensitive matching, any-cell scope, and a hard 50-row ceiling. It omits whether the operation is read-only (implied), how results are ordered, and whether the cap truncates silently or signals more results exist.

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

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

A single sentence that front-loads the resource, then the matching rule, then the cap – no filler and nothing buried.

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 read tool with no output schema and no annotations, the definition covers matching and limits but says nothing about the returned shape (row structure, field names) or ordering, which an agent needs to consume the results.

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 as 'text to look for in any cell' while 'limit' has only type/bounds. The description adds case-insensitivity for query and restates the 50 cap already implied by limit's maximum, so it contributes modest meaning beyond the schema.

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 ('Rows of the Send A Parcel Compare dataset whose cells contain the query'), including matching semantics and the 50-row cap, so the agent knows exactly what the tool returns. It does not explicitly contrast itself with siblings like dataset_row or dataset_top, so it falls 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?

No guidance on when to use this versus dataset_row, dataset_top, or dataset_columns, and no exclusions or prerequisites. The 'search' framing implies free-text lookup but nothing routes the agent between the 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?

With no annotations, the description carries the full burden, and it does disclose meaningful data-handling behavior: grouping commas and currency values are parsed, and non-numeric rows are excluded and counted. It does not, however, say whether the operation is read-only (implied), how errors surface for a non-existent or non-numeric column, or the shape of the returned values.

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 tight sentence that front-loads the returned metrics, with a compact parenthetical carrying the edge-case behavior. Nothing is redundant, though the parenthetical is slightly dense.

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 one-parameter aggregation tool with no output schema, the description covers the metric list and the key edge cases (currency/commas, non-numeric rows). Only the mechanics of identifying a valid numeric column are left unstated.

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 0% description coverage for the single 'column' parameter, so the description must compensate. It adds useful semantics by specifying the column must be numeric and describing how non-numeric rows are handled, but gives no detail on naming/exact-match rules for supplying the column identifier.

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 operation (aggregate summary statistics) on a specific resource (a numeric column of the Send A Parcel Compare dataset) and enumerates the exact metrics returned (count, min, max, mean, median, sum). This clearly separates it from siblings like dataset_columns, dataset_compare, and 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?

There is no guidance on when to choose this tool over siblings such as dataset_columns or dataset_top, and no stated preconditions (e.g. that the column must exist and be numeric). Usage is only implied by the tool name and the word 'numeric column'.

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 but discloses little: it does not say whether results are ordered, how ties are broken, what the default limit is, whether limit caps the dataset scan, or what the return shape looks like. Only the core ranking behavior is conveyed.

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 with no waste, and the core behavior (ranking by a numeric column) is front-loaded. The em-dash gloss aids comprehension without 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?

For a simple three-parameter tool with no output schema, the description covers purpose but omits limit semantics, ordering/return behavior, and default behavior for the one required column argument. Adequate but with clear gaps 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 description coverage is only 33% (only 'ascending' is documented), so the description must compensate. It adds one useful constraint beyond the schema — that the target column must be numeric — but says nothing about 'limit' (bounds, default, effect), so the gap is only partly closed.

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: ranking the highest/lowest rows of the Send A Parcel Compare dataset by a numeric column, and renders the intent in natural language ('which is the most/least X'). It is clearly distinguishable from siblings like dataset_stats or dataset_search. It stops short of explicitly naming which sibling to use when, but the purpose itself is unambiguous.

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

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

The phrase 'which is the most/least X' implies the query shape this tool answers, so usage is inferable, but there is no explicit when-to-use vs alternatives (e.g., versus dataset_search or dataset_stats) and no stated preconditions. It lands at implied-usage 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?

With no annotations, the description carries the full burden and does reasonably well: it disclaims side effects ("Nothing is bought, ordered or paid; no quote is guaranteed; it is free") and previews the returned content (recipients, consent wording, confirmation). For a 0-param read/explain tool this is solid, though it doesn't say anything about format or limits of the returned text.

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?

It is short and front-loads "Read first," which is good. But it spends words restating the title's caveats ("no quote is guaranteed" / "Nothing is bought, ordered or paid" / "it is free" overlap), and the long colon-joined middle sentence is denser than it needs to be.

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 no-parameter, no-output-schema tool, the description covers both the purpose and the nature of the output (who receives details, consent wording, confirmation method), which is sufficient for an agent to decide to call it. Slightly more on the form of the returned text would close the remaining 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 input schema has zero parameters, so the baseline is 4; there is nothing for the description to disambiguate on this axis.

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 the tool's job: it explains in plain language what submit_enquiry does and returns the surrounding detail (recipients, consent wording, confirmation path). This distinguishes it from submit_enquiry (the action) and enquiry_fields (the schema), though the framing in terms of another tool is slightly indirect rather than stating "this tool returns X".

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 sequencing hint that this should be consumed before the enquiry flow, which is useful implied guidance. However, it never names the alternative tools explicitly or states when this is unnecessary, leaving the when/when-not to inference.

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

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

With no annotations, the description carries the full burden and does disclose the shape of the returned data (key, label, type, required flag, help text, allowed options) and the keying convention for downstream submission. It does not explicitly state that the call is read-only or whether it is cached/static, but for a zero-parameter metadata listing the disclosure is solid.

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 the resource and followed by the actionable routing hint. Minor wordiness in 'whether required, help text and the allowed options where there are any,' but nothing that wastes real space.

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 properly takes on the job of enumerating the returned attributes, and with zero parameters there is nothing else an agent needs before calling it. Only the absence of any note on staleness or read-only nature keeps it from a 5.

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 the baseline is 4; the description goes slightly further by explaining how returned field keys map onto submit_enquiry answers, giving the output a semantic anchor.

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 ('Every field of the Send A Parcel Compare enquiry') and enumerates what the tool returns (key, label, type, required, help text, options), so an agent knows this is a field-metadata fetch rather than an enquiry description. It does not explicitly differentiate itself from the sibling enquiry_describe, which is the only gap.

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 closing sentence routes the agent downstream: 'Pass answers to submit_enquiry keyed by field key,' which makes the when-to-use context (call this to learn the schema before submitting answers) clear. No explicit when-not conditions or alternatives are stated, but the intended workflow 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?

With no annotations, the description carries the full burden and discloses the complete flow: validation, return of a summary/consent line/token, the need for explicit person approval, the confirmation-token second call, and the required email click before providers see the enquiry. It also explains the exact consent meaning.

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 front-loaded with purpose and caveats, then clearly structured by steps. It is somewhat long and repeats the consent text already present in the schema, but the repetition supports the two-step contract and every sentence remains functional.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the two-step workflow, nested answers object, lack of output schema, and no annotations, the description is complete enough for correct invocation. It covers inputs, sequencing, consent, and post-submission behavior without relying on missing structured fields.

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 100%, so all parameters are documented in the schema. The description adds value by explaining that answers are keyed by enquiry_fields keys, that confirmation is the token from step 1, and that consent must be true in both steps.

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 ('Submits') and resource ('an enquiry to Send A Parcel Compare') and immediately distinguishes it from a purchase or guaranteed quote. It also names the sibling prerequisite implicitly by referring to field keys from enquiry_fields.

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 explicit two-step instructions with conditions: Step 1 with answers and consent=true, show the summary and consent line; Step 2 only if the person agrees, with the same answers, consent=true, and the confirmation token. It also clarifies what the tool is not (not a purchase, not a guaranteed quote).

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