iana-registries-mcp-server

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

Annotations already cover readOnly/idempotent/openWorld, so the bar is lower, yet the description adds real behavior: an ambiguous multi-subregistry request returns a list rather than records, nested tables list rather than expand, and large registries page via cursor. These are non-obvious runtime traits that annotations do not convey.

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 purpose is front-loaded and there is no filler, but the single value-matching sentence is a deeply nested, hard-to-parse parenthetical that duplicates the schema's own exhaustive value semantics, inflating length without adding proportionate value.

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 7 parameters, complex filtering semantics, and an existing output schema, the description supplies the key non-schema behavior an agent needs (sub-registry fallback to a list, nesting behavior, pagination). Return-value formatting is rightly left to the output schema, so coverage is nearly complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description's detailed value-matching rules (digit vs 0x comparison, range rows) largely restate what the schema already documents, and it adds only marginal extras like the 'rec = Recommended column' convention.

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 ('Read records from any IANA XML registry by id') with concrete examples (tls-parameters, protocol-numbers). It also distinguishes itself from the sibling iana_search_registries by naming it as the id-discovery path, so an agent can tell the two apart without opening either 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?

Names the alternative for id discovery ('Find ids with iana_search_registries') and explains the alternative flow when multiple sub-registries exist (listing instead of records). It does not, however, contrast itself against the many iana_lookup_* siblings, so the when-to-use picture is clear but not exhaustive.

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?

Drops the annotation bar and goes well past it: a hard budget of 20 Datatracker requests per call, per-id request costs (1 for an RFC/series plus one for its series, 3-4 for a draft), the request-order allocation rule, and the request_limit failure reason for the remainder. It also discloses unknown ids return found: false and that canonical aliases resolve once, which an agent needs to predict 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?

Front-loads the core operation and the pagination trio before the long input-format inventory, and every sentence carries information. It is dense and the accepted-format examples partly duplicate the schema's items description, keeping it short of a 5.

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 tool with pagination, request budgeting, and alias resolution, the description covers continuation, failure semantics, and return shape (RFC vs draft vs series fields). With an output schema present it did not need to explain returns, yet the extra detail is accurate and useful.

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

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

Schema coverage is 100%, so baseline is 3, but the description adds real semantics: canonical alias deduplication before selecting ten distinct ids, the exact continuation contract between next_ids_offset and ids_offset, and the one-string comma/semicolon/newline form. The accepted-id-format list is largely mirrored in the schema, so it does not push higher.

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: get the current status of RFCs, Internet-Drafts, or BCP/STD/FYI series. The scope is far from the sibling lookup tools (registries, media types, ports, HTTP fields), so no ambiguity arises about which tool handles document status.

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 clear operational guidance: how to paginate with deferred_ids/deferred_count/next_ids_offset, and to retry failed ids separately with the same original ids. It does not explicitly name alternatives or exclusions, but no sibling overlaps this resource, so the missing step is minor.

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?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond that: the expected return shape (registration status, Structured Field type, defining reference) and the important negative-result caveat that a miss only means IANA has no entry rather than that the header is invalid.

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?

Four sentences, front-loaded with the purpose before the parameter contract, and each sentence carries distinct load: what it does, how to call it, what comes back, and how to read a negative result. Nothing is 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?

With an output schema present, the description needn't enumerate return fields, yet it still previews them usefully. It covers mode selection, status filtering, and the false-negative caveat; pagination and limit clamping are left entirely to the schema, which is acceptable but leaves the description one notch short of fully self-contained for a multi-mode lookup.

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 each of the five parameters is already documented in the schema, including the name/keyword mutual exclusion, case-insensitivity, keyword token matching, and the limit clamping behavior. The description largely restates these, adding the concrete example "Cache-Status" but no syntax or semantics not already present.

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 ("Look up a registered HTTP field name") and scopes it precisely to header/trailer field names, which distinguishes it from siblings like iana_lookup_http_status, iana_lookup_media_type, and iana_lookup_uri_scheme. An agent can route correctly 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 invocation guidance ("Pass exactly one of `name` ... or `keyword`") and a clear condition for the keyword mode ("words matched against field names and comments"). It stops short of naming alternate sibling tools for when the caller actually wants status codes, language tags, or registry browsing, so it is clear context without explicit alternatives.

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?

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuine behavioral context beyond that: the fields returned (phrase, class, reference with section, temporary/obsoleted/unused flags) and the not-found behavior ('found: false with the unassigned range it falls in'). Since an output schema exists, this return detail is partly redundant, capping it at 4.

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 but well-front-loaded sentence: the primary action and mode selection come first, then the return shape. No filler sentences, though the packed return-value clause makes it heavier than strictly necessary given an output schema exists.

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 4-param, no-required-param lookup with a full output schema, the description covers everything an agent needs: the two mutually exclusive input modes, the valid code range, and the not-found semantics. Nothing material 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 description coverage is 100%, and the schema already documents the code/keyword mutual exclusivity, ranges, and the limit clamping behavior. The description largely restates this ('Pass exactly one of code or keyword', the 100–599 range, the 'too many' example), adding little the schema does not already carry. Baseline 3 applies.

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 (look up / search) and resource (HTTP status code in the IANA registry, reason phrases), with the dual mode (code vs keyword) made explicit. This clearly distinguishes it from siblings like iana_lookup_http_field, iana_lookup_port, and iana_get_registry_records.

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 a clear selection rule: 'Pass exactly one of `code` (100–599) or `keyword`'. This tells the agent when each input mode applies. However, it never names a sibling alternative or states when NOT to use this tool (e.g. vs. iana_search_registries), 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?

Goes well beyond the annotations (readOnlyHint/openWorldHint/idempotentHint) by disclosing result behavior: tag is decomposed into language/extlang/script/region/variant/extension/private-use parts, deprecated subtags report a preferred value, a canonical tag is returned when valid, and extension singleton allocation "never validates extension content or changes base validity." It also notes that a subtag registered under several types (e.g. "TW") lists the other types, which is genuinely useful runtime 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?

Front-loaded with the core action and mode split, then layered with progressively finer behavioral detail. The later sentences are dense and pack several facts each (allocation semantics, multi-type subtags), which is efficient but slightly heavy for a description of this length.

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 an output schema present, the description needn't document returns, yet it still explains the shape of the result (canonical tag, decomposed parts, deprecated preferred-value) and the nuance that extension metadata is optional and non-validating. Combined with annotations covering the safety profile and a fully documented schema, nothing needed to invoke this 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 description coverage is 100%, so the baseline is 3; the description still adds framing beyond the schema by tying each parameter to a mode and clarifying that tag mode always returns every part of the tag while description mode is the searchable/paginatable path. It does not add new syntax or format detail not already present in the parameter descriptions, so it stays short of 5.

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?

Opens with a specific verb pair and resource: "Parse and validate a BCP 47 language tag against the IANA Language Subtag Registry, or search subtags by description." The dual mode (validate a tag vs. search by description) is explicit, and the tool name plus scope make it immediately distinguishable from sibling lookup tools such as iana_lookup_media_type or iana_lookup_uri_scheme.

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?

"Pass exactly one of `tag` ... or `description`" gives unambiguous mode-selection guidance and is reinforced by examples for each mode. It does not, however, name alternatives or any when-not condition relative to sibling lookup tools, so an agent gets clear context but no explicit routing exclusions.

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

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

Annotations already declare readOnly/openWorld/idempotent, so the safety profile is covered. The description adds genuine behavioral context beyond them: exact `type` lookups read the registration template, some types lack templates (`template.available: false`), and deprecated/obsoleted types are reported with replacements. This is substantive disclosure, not restatement.

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 verb and the mode choice, and every sentence carries information (template behavior, deprecation reporting, x- exclusion). It is dense and slightly long, but no sentence is filler.

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

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

A read-only lookup with an output schema and full annotation coverage needs less from the description, and this one still covers template availability, deprecated replacements, and keyword matching limits. Nothing essential for correct invocation appears 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 description coverage is 100%, so the baseline is 3. The description reinforces the mutually-exclusive type/keyword semantics and the ';'-suffix stripping rule, but these points are already stated in the schema property descriptions, so it adds little new parameter-level meaning.

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

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

States a specific verb and resource ('Look up registered media (MIME) types') and is clearly distinguishable from siblings like iana_lookup_http_field or iana_lookup_uri_scheme. An agent can identify the target registry without opening the 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 mode selection ('Pass exactly one of type or keyword'), describes what keyword does and does not match ('never against file extensions'), and states a when-not case (unregistered 'x-' types are not in the registry). It stops short of naming a sibling as an alternative, so it does not reach a 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?

Annotations already establish readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description still adds real behavior beyond them: what is returned (organization and OID prefix), what is explicitly not returned (contact details), and the scope boundary that sub-arcs are enterprise-assigned rather than IANA-assigned.

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 action and resource, then the input constraint, then return semantics and caveats in a compact block. The input-selection sentence partially duplicates the schema's own "Pass this or organization, not both" wording, which is the only real slack.

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 an output schema present, the description does not need to enumerate return fields, and annotations carry the safety profile. What remains — how to supply the identifier, mutual exclusivity, the scope caveat about enterprise-assigned arcs, and the absence of contact data — is exactly the residual an agent needs to call this 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 description coverage is 100%, so the schema already documents the pen pattern, the OID example, the mutual exclusivity, and the limit clamping behavior in more detail than the description. The description's restatement of the either/or constraint and the OID example adds no meaning beyond the schema, so baseline 3 is appropriate.

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 (look up) and a precisely named resource (Private Enterprise Number), with the canonical form and both accepted input shapes. It is immediately distinguishable from siblings such as iana_lookup_port, iana_lookup_media_type, or iana_lookup_uri_scheme, which target entirely different registries.

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?

"Pass exactly one of pen ... or organization" gives explicit selection guidance between the two input modes, and the note that arcs below the enterprise number are assigned by the enterprise rather than IANA implicitly warns against using this tool to resolve sub-arcs. It stops short of naming an alternative tool for those cases, so it is clear context without full when-not routing.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), so the bar is lower, and the description adds genuine behavioral context: results are split per transport, unassigned ports return the containing registry range row, ports are bucketed into System/User/Dynamic ranges, and DNS-SD names appear portless. Some of this overlaps the output schema, which limits it to a 4 rather than a 5.

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

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

Three sentences, front-loaded with purpose, then the mutually exclusive inputs, then result semantics. No filler, no restatement of the title, and the edge cases (unassigned ports, DNS-SD) are compressed into single clauses.

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 an output schema, 100% schema coverage, and full annotations, the description only needs to carry selection and scoping information, which it does: three modes, transport behavior, and the port-classification semantics. Nothing an agent needs in order to choose and call the tool 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 description coverage is 100% and every parameter already documents its own constraints (limit clamping, offset paging, transport filtering, mutual exclusivity). The description's restatement of the 'exactly one of' rule and keyword matching adds nothing the schema does not already say, so the baseline 3 applies.

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?

Starts with a specific verb+resource ('Look up IANA service name and transport protocol port assignments'), which is immediately distinguishable from siblings that look up media types, http fields, language tags, or PENs. The three lookup modes and the result shape are stated up front, so an agent can identify the tool without opening the 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 description gives clear invocation routing: exactly one of `port`, `service`, or `keyword`, with an example value for each mode ('postgresql', 'network time'). It does not, however, state when to prefer this tool over siblings such as iana_search_registries or explain what happens if zero or multiple mode parameters are supplied, so it falls short of explicit when/when-not 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?

Annotations already establish readOnly/idempotent/openWorld, so the bar is lower, and the description usefully adds the input-normalization behavior (a trailing ":" or "://" is ignored) and previews the returned fields. It doesn't discuss pagination limits or result-count behavior, which would have pushed it higher.

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, front-loaded with the purpose, then the invocation rule, then the return context. No filler and nothing important 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?

An output schema exists, so return values need not be explained in depth, and the annotations cover the safety profile. Combined with a 100%-documented parameter schema, the description supplies everything else an agent needs to call it correctly.

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

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

Schema description coverage is 100%, so limit, offset, status, scheme and keyword are all already documented with ranges, defaults and mutual-exclusion notes; baseline 3 applies. The description restates the scheme/keyword exclusivity and the normalization rule but adds nothing the schema does not already carry.

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 ("Look up a registered URI scheme") that immediately separates it from the other iana_lookup_* siblings by resource type. It also names both lookup modes (exact scheme vs keyword), so an agent knows what the tool covers without opening the 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 a concrete selection rule — "Pass exactly one of `scheme` ... or `keyword`" — which tells the agent how to choose the mode. It does not, however, say when to prefer this over iana_search_registries for broader queries, so the alternative-routing is left implicit.

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?

Annotations already cover readOnly, idempotent, and openWorld, so the safety profile is handled. The description adds genuinely useful behavioral context beyond the annotations: it states the output includes registry/sub-registry ids plus registration procedure and defining documents, and asserts full coverage of the IANA protocol registries index.

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 sentences that are front-loaded with the core action and resource, then scope, then output/workflow. Every sentence contributes, though the keyword examples and coverage claim make it slightly longer than strictly necessary.

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 an output schema present and 100% parameter coverage, the description need not explain return values. It supplies the scope and the relationship to iana_get_registry_records, which is the remaining value-add; only explicit sibling differentiation 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 all three parameters (query, limit, offset) are already documented, including token matching and pagination behavior. The description's example queries reinforce the schema but add no syntax or format detail beyond it, so the baseline 3 applies.

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 ('Find') and resource ('IANA protocol registries and sub-registries'), and explicitly scopes the search to titles and protocol categories with concrete examples. It also distinguishes itself from the sibling iana_get_registry_records by explaining that this tool produces the ids that tool consumes.

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 clearly names the downstream consumer iana_get_registry_records, implying a search-then-fetch workflow so an agent knows why to call it. However, it does not explicitly contrast itself with the many lookup siblings (e.g. iana_lookup_port), leaving some routing inference to the agent.

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