site

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

There are no annotations and no output schema, so the description carries the full behavioral burden. It does disclose the return contents (columns, numeric flags, row count, provenance banner), which is genuinely useful, but it says nothing about the response format, whether the fields are keyed by name, or any access constraints.

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 enumerates the payload, the second gives the call-ordering instruction. Nothing is redundant and the salient content leads.

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 does the work by stating what is returned, which is enough for an agent to decide to call it. It could still clarify the shape of the returned columns list and provenance banner, but nothing essential is missing for a zero-parameter schema 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?

The tool takes zero parameters, so per the baseline there is nothing for the description to disambiguate. The absence of any parameter discussion is correct here rather than a 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 names a concrete resource (the Asbestos Survey Cost dataset) and enumerates exactly what it returns: columns, numeric flags, row count, and provenance banner. That is well beyond a tautology, but it does not differentiate itself from siblings like dataset_stats (row count/numeric) or dataset_provenance (provenance banner), so it stops 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 explicit ordering guidance — 'Call this first to learn the schema' — which clearly signals the tool's role as an entry point before other dataset_* calls. It does not, however, name an alternative or state when a sibling (e.g. dataset_stats) should be preferred instead.

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

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

With no annotations, the description carries full behavioral burden. It discloses only the result ordering ("in the order given"), which is useful. It says nothing about whether the hardcoded dataset can vary, case sensitivity, what happens for missing values, or any limits on how many values can be compared.

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 tight sentence, which is good, but the front-loading is weak (the reader must reach the em-dash to learn the tool's actual purpose) and the hardcoded dataset name inflates the sentence without helping tool selection.

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 annotations and no output schema, so the description is the only source of behavioral and return information, and it provides neither. The value-count limit, the fixed dataset, and the shape of the returned rows are all undisclosed, leaving real gaps for a filtering tool.

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

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

Schema description coverage is 0%, so the description must compensate, and it partly does: "column is any of the given values, in the order given" explains both parameters and clarifies that the values array is a match-any list whose order matters. It omits the 2–10 item constraint and the non-empty string requirement, so the schema constraints remain unexplained.

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 conveys that it returns rows of a specific dataset filtered by a column matching any of the given values, in the given order, and frames it for "X vs Y" questions. However it is a noun phrase with no verb, and it hard-codes "Asbestos Survey Cost dataset" rather than treating the dataset as a parameter, which muddies what resource is actually being operated on.

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" is a genuine usage cue that pairs with the title's "Compare rows side by side." But it names no alternatives and gives no exclusions versus the clearly overlapping siblings dataset_search, dataset_row, and dataset_top, so the agent must still guess whether this or a search tool is correct.

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 enumerates the returned fields (source, date, licence, citation), which is the key behavioral fact for a zero-parameter getter. It omits auth/rate-limit considerations, but for a static read-only metadata call the gap is minor.

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: the first lists returned content, the second states the use case. Front-loaded 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?

There is no output schema, so the description must convey return content, and it does by naming the four fields an agent needs. The only shortfall is not specifying the response format or which dataset identifier is used, but for a no-input provenance lookup this is largely 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 to clarify and the baseline is 4. The description correctly does not invent parameters.

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, computed date, licence, citation) for a named dataset, so an agent knows exactly what it gets. It does not name or contrast with siblings like dataset_stats or dataset_columns, but the provenance/citation scope 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?

"Read this to attribute a figure correctly" gives a clear condition for use: when attribution/citation is needed. No explicit exclusions or named alternatives are provided, but the intended context is stated rather than 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 supplied, so the description carries the full burden, and it does disclose two real behavioral traits: matching is exact and case-insensitive, and the target dataset is fixed. It says nothing about result cardinality, limits, or what happens with an unknown column name, leaving meaningful gaps for a no-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 sentence with no filler, and the key constraint (exact, case-insensitive match) is front-loaded before any elaboration. The phrasing is slightly awkward but wastes nothing.

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 explain what a matching row looks like and whether multiple rows can be returned. Instead it stops at the matching predicate, leaving the return shape and cardinality entirely undocumented for a lookup tool.

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

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

Schema description coverage is 0%, with only minLength constraints on column and value. The description establishes the column/value relationship and the exact-match semantics, but gives no hint about valid column names (e.g. that dataset_columns enumerates them) or value 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 states a specific operation (return rows where a column equals a value exactly) against a named dataset, which is clearer than the bare name. It does not, however, differentiate itself from siblings like dataset_search or dataset_top, which invite similar lookups.

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 this tool is preferable to dataset_search or dataset_top, nor any mention of prerequisites or exclusions. The phrase 'equals a value exactly' implies an exact-match niche, but the agent must infer that this is the delimiter versus a fuzzy search.

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

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

With no annotations, the description carries the full burden. It does disclose two useful traits: matching is case-insensitive across any cell, and results are capped at 50 rows (a silent truncation an agent must know about). It says nothing about ordering, permissions, or what a returned row contains.

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 dataset, match semantics, and result cap all appear immediately.

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 and no annotations, so the description must stand alone, yet it omits result ordering, pagination behavior when more than 50 rows match, and the shape of a returned row. Adequate for a simple search but leaves real gaps for an agent planning multi-step retrieval.

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% (only 'query' is described). The description compensates by defining the query semantics (case-insensitive, matches any cell) and by explaining the effective 50-row ceiling that governs the undescribed 'limit' parameter, so both parameters gain 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 (search) and resource (rows of the Asbestos Survey Cost dataset), plus scope (cells containing the query, up to 50). An agent can tell it apart from dataset_row/dataset_top by the any-cell substring semantics, 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?

No when-to-use guidance and no mention of alternatives in a family that includes dataset_row, dataset_top, and entities_search. An agent must infer that this is the free-text lookup tool rather than an exact-row or ranked query 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, and it does disclose meaningful data-handling behavior: grouping commas and currency symbols are normalized, and non-numeric rows are excluded and reported as a count. It stops short of describing failure behavior (e.g., a fully non-numeric or misspelled column) or the response 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?

A single dense sentence that front-loads the returned metrics and follows with scope and handling rules, so scanning it answers 'what do I get' immediately. The parenthetical adds real information rather than padding, though the sentence is tightly packed.

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, enumerating the returned statistics in the description is exactly what is needed. The remaining gap is the undocumented format of the 'column' argument, which matters given 0% schema coverage.

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 adds only an implied constraint (the column must be numeric, and belongs to the Asbestos Survey Cost dataset) but never states the expected format, such as a header name or case sensitivity.

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 and enumerates exactly what is computed (count, min, max, mean, median, sum) on a numeric column of a named dataset, which is far more concrete than a generic 'stats' label. It does not, however, explicitly differentiate itself from siblings like dataset_compare or dataset_top, so the agent must infer the boundary.

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 tool name and the listed outputs: it is the tool for descriptive statistics on one numeric column. There is no statement of when to prefer it over dataset_top, dataset_compare, or dataset_search, and no prerequisites or exclusions are given.

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

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

No annotations are provided, so the description must carry the full behavioral burden. It discloses the core operation (highest or lowest rows by a numeric column) but does not state whether the operation is read-only, how ties or nulls are handled, or what the return format looks like. Core behavior is clear, but side-effect and edge-case transparency is limited.

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 definition is a single front-loaded sentence with a concrete example use case. It is appropriately sized and contains no wasted text.

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 ranking tool, the description gives enough to understand the core operation. But with no annotations, no output schema, and low schema description coverage, it omits limit behavior, default direction details beyond the schema, and return-shape expectations. It is minimally adequate but leaves 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 only 33%, so the description should compensate. It adds useful meaning by saying the column must be numeric, which the schema does not state, and its highest/lowest phrasing aligns with the ascending parameter. However, it says nothing about the limit parameter or its default/range, leaving a meaningful 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 clearly states that the tool returns the highest or lowest rows of a named dataset by a numeric column, which is a specific and understandable operation. It does not explicitly differentiate itself from sibling tools such as dataset_stats or dataset_row, so it falls short of the highest clarity tier.

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 tool's intended use for ranking questions, but there is no explicit guidance on when to choose it over alternatives like dataset_stats or dataset_search. Usage is inferable 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?

With no annotations, the description carries the full behavioral burden and does so well: no purchase/order/payment, no guaranteed quote, free, plus it discloses return contents (recipients, consent wording, confirmation). It omits any rate-limit or auth context, but for a read-only info tool this 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 operative "Read first" directive, and every clause earns its place. The inclusion of the site name "Asbestos Survey Cost" is mildly extraneous but not costly.

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-param, no-annotation, no-output-schema description-only tool, the description explains the return content itself (recipients, consent wording, confirmation), compensating for the missing output schema. It is essentially complete for an informational 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 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?

It states a specific verb+resource (describe/enquiry) and explicitly frames itself as documentation of what submit_enquiry does, distinguishing it from the sibling that actually submits. The framing is slightly meta/circular (a describe tool announcing that it describes), which keeps it from being 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 clear ordering guidance relative to submit_enquiry, and the negative framing (not a purchase, not a quote) clarifies scope. It does not name explicit when-not conditions or other alternatives, but the sequencing intent 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. It does disclose the return content in detail (including conditional allowed options), which is more than the title alone. However, it never states that this is a side-effect-free read, nor anything about scope, size, or auth, so the behavioral profile is only partially 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 tight sentences, front-loaded with the resource and its contents, then a single actionable follow-up. No filler, no redundancy with 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?

With no output schema and no parameters, the description must describe the return payload, and it does so reasonably completely across six aspects. Minor gaps remain (no mention of whether one or many enquiries exist, ordering, or pagination), but nothing essential is missing 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?

The tool takes zero parameters, so the baseline is 4. The description still adds useful meaning by tying the returned 'field key' to how answers must be keyed when calling submit_enquiry, which clarifies the semantic link between output identifiers and the sibling tool's 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?

States precisely what is returned (every field of the Asbestos Survey Cost enquiry) and enumerates the shape: key, label, type, required flag, help text, and allowed options. It is also distinguishable from the sibling submit_enquiry, which it names, so an agent can pick it out 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?

The second sentence gives a clear workflow: 'Pass answers to submit_enquiry keyed by field key,' which tells the agent this is the discovery step before submission. It stops short of explicitly stating when not to use it or contrasting with enquiry_describe, so it is context-rich rather than fully prescriptive.

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 behavioral burden and does disclose real traits: Bearer auth is required, pages are metered per key per day, and an unauthenticated call returns guidance on obtaining a key. It omits whether pagination terminates or what provenance output looks like, but adds substantial context beyond the schema.

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 no filler, front-loaded with the resource scope before the operational constraints. 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 paginated export with no annotations, the description covers auth, metering, page size, and error behavior. Missing only pagination termination semantics and confirmation of the response shape, which is minor for this tool.

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

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

Schema description coverage is 0%, so the description must compensate. It clarifies the page size (200) but never explains the 'page' parameter, its default, or the default pageSize, leaving half of the parameter semantics 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?

States a specific verb and resource: export every entity of the Asbestos Survey Cost register, paginated, with provenance. This distinguishes it from filtering siblings like entities_search or entities_in, though those siblings are never 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 phrase 'Every entity' implies a bulk/full-register export as opposed to the lookup or search tools, but there is no explicit when-to-use or when-not-to-use guidance. The auth prerequisite is stated, which is useful routing context.

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 only partly discharges it. It does disclose pagination behavior ('50 a page'), which is genuinely useful, and notes the optional service filter. It omits ordering, what an entity record contains, and any permission/auth context.

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 the resource stated first and the scoping/filter constraints following. It is compact with no wasted clauses, though the parenthetical and 'The Asbestos Survey Cost register entities' construction read somewhat awkwardly.

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 four parameters at 0% coverage, the description covers the essentials (region, optional service, pagination size) but leaves gaps around page navigation, return shape, and entity contents that an agent would need for full confidence.

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 usefully clarifies that region accepts either an id or a name (a state or jurisdiction) and that service is an optional filter, covering two of four parameters. It says nothing about the 'page' parameter and only indirectly implies pageSize via '50 a page'.

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

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

The description clearly states the resource (register entities) and scope (one region, optionally one service), which distinguishes it from the broader entities_search and single-record entity_lookup siblings. The verb is implicit rather than explicit, and the awkward 'The Asbestos Survey Cost register entities' phrasing slightly obscures the action, but an agent can tell what it returns and for what locale scope.

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 use this tool versus entities_search, entities_export, or entity_lookup. The region+optional-service framing implies a usage context, but no conditions, exclusions, or named alternatives are given, leaving the agent to infer when this is the right choice.

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 implies a read-only metadata lookup by describing returned content, but never states that it has no side effects, returns no rows, or how large/heavy the response is. Adequate but thin 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?

The core content is front-loaded in a single sentence followed by a terse directive, which is efficient. However, the duplicated word "register register" is a noticeable defect and the enumeration is slightly run-on, costing structure points.

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 what the response contains (fields, counts, regions, services, identifier schemes, citation). For a zero-argument metadata tool this is close to sufficient, with only the return format and size left unspecified.

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 at the parameter level, and it correctly implies the tool is invoked without 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 concrete resource (the Asbestos Survey Cost register) and enumerates what it returns: fields, entity counts, regions, services, identifier schemes, and citation guidance. An agent can tell this is a schema/metadata introspection tool, though it does not explicitly contrast itself with siblings like dataset_provenance or dataset_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?

"Call this first" gives explicit ordering guidance for the discovery flow, which is a genuine when-to-use signal. It stops short of naming an alternative or stating when-not to call it, so it falls just under full marks.

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

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

With no annotations, the description carries the full burden. It usefully discloses a result cap ('Up to 50 rows') and substring matching semantics across multiple fields, but says nothing about ordering, pagination beyond the cap, or the read-only nature of the 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?

Two tightly packed sentences with no filler; the matching scope is front-loaded and the row cap is stated tersely. The enumerated field list is dense but each item 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 four-parameter, no-annotation, no-output-schema search tool, the description covers query scope, optional filters, and result size adequately. What a returned row contains is left implicit, though the entities_schema sibling can fill that 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?

Schema description coverage is 0%, so the description must compensate, and it does: q is defined as a contains-match across five fields, region accepts an id or name, service accepts a slug or name, and limit is bounded at 50 rows. Only the limit's default behavior is left unspecified.

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 action (search entities in the Asbestos Survey Cost register) and enumerates the exact fields matched by the query, so an agent can tell it apart from singular lookups like entity_lookup. It does not explicitly contrast itself with siblings such as entities_in or entities_export, 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 description implies free-text search usage but never states when to choose this over entity_lookup, entities_in, or entities_export, nor any preconditions. An agent must infer the boundary 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?

No annotations are supplied, so the description carries the full burden. It does disclose the key behavior that matters here: matching is exact, and the return is the whole record with its page. It omits not-found behaviour, whether slug and scheme+value are alternative selectors or combined, and any auth or rate-limit context.

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, front-loaded sentence: resource first, then the two lookup paths, then the matching semantics and return shape. No filler and nothing repeated from the schema.

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 helpfully states it returns the whole record plus its page, covering the return value. But for a tool with three parameters and zero required fields, it leaves the selector logic (slug vs scheme+value), failure behaviour, and any access constraints 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 coverage is only 33% (only 'scheme' is documented inline), so the description must compensate. It explains the scheme+value pairing and gives an example ('lei') matching the schema's own examples, and identifies slug as a page-slug alternative. It does not clarify the mutual exclusivity or the required combination of these two selector paths, leaving ambiguity for a 0-required-param tool.

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

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

States a specific verb and resource: retrieve one register entry ('a firm') either by register identifier (scheme + value) or by page slug. It is distinguishable from the sibling entities_search because it explicitly says 'Exact match', implying search is the fuzzy alternative. It stops short of naming that sibling outright, so it is clear but not 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?

The phrase 'Exact match' implicitly tells the agent to use this tool when it holds a precise identifier rather than a query string, which is useful implied guidance. However, it never states when NOT to use it, names no alternative (entities_search, entities_in, entities_export), and says nothing about what happens on a miss or whether slug and scheme/value are mutually exclusive.

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 that nothing is purchased or guaranteed, that step 1 only validates and returns a summary/consent line/token, that step 2 requires the token, and that the person must click an emailed link before any provider sees the enquiry. Scope limits ('up to three surveyors') and revocation ('can stop any more firms') are also stated.

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 most important disambiguation ('NOT a purchase') and then walks the two steps in order, which is the right structure for a gated flow. It is long and the full consent text is reproduced verbatim from the schema, which is mild duplication, but the length is otherwise justified by the consent mechanics.

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 return values, and it does: step 1 returns a summary, consent line and confirmation token, and step 2 returns a submitted enquiry that triggers a confirmation email. Combined with the nested 'answers' object and full schema coverage, an agent has everything needed to drive the flow 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, but the description adds real semantics the schema lacks: 'confirmation' is only used in step 2 and must be the token returned by step 1, and consent must be tied to the person actually having read the quoted consent text. That is meaningfully more than the field-level descriptions provide.

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 Asbestos Survey Cost') and immediately draws the key boundary against likely confusion: 'NOT a purchase, NOT a guaranteed quote.' An agent can distinguish this from the read-only siblings (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?

Gives explicit two-step usage with the exact condition that gates step 2 ('only if the person agrees'), and points at enquiry_fields as the source of the field keys. It also states the prerequisite for consent=true, so there is no inference left about when it is safe to call.

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