SealGate

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds value by specifying the required authentication (api_key issued from the admin screen) and the exact data returned, which is beyond the annotations. It does not cover error cases or rate limits, but the annotation bar is lower.

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 a single, front-loaded sentence with no filler. It immediately states the main purpose and then adds the required credential in a parenthetical. Every word contributes meaning.

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 tool with one parameter, no output schema, and rich annotations, the description is complete. It tells the agent what the tool returns, what input is needed, and where the api_key comes from, leaving no critical 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 coverage is 100%, so the baseline is 3. The description adds minor context by clarifying the api_key must be issued from the admin screen, which is not in the schema. This is useful but not essential for correct invocation.

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 ('returns'), a specific resource ('the app for this API key'), and enumerates the returned fields (rp_id, allowed origins, password coexistence expiration, Webhook URL). This clearly distinguishes it from siblings like get_stats and get_integration_guide, which have different purposes.

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 usage: use this tool when you need the app settings associated with an API key. However, it does not explicitly state when not to use it or name alternatives, leaving the agent to infer the appropriate context from the purpose.

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=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile. The description adds value beyond that by disclosing the return format (Markdown) and the content scope. No contradictions between description and annotations, and no hidden behaviors (no side effects, no auth requirements) are omitted for a read-only guide fetch.

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 verb and resource, then packs the content topics and output format without any filler. Every element earns its place, and nothing is redundant with the annotations or 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?

For a parameterless, read-only guide retrieval tool with no output schema, the description is quite complete: it names the topics covered and the return format. It could arguably enumerate more detail about the guide's structure, but the main content categories are present and nothing essential for an agent to call it correctly is missing.

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

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

The tool has zero parameters and schema description coverage is trivially 100%, so there are no parameter semantics for the description to clarify. Per the baseline for 0-parameter tools, a 4 is appropriate since nothing is missing; the description focuses appropriately on what the tool returns instead of 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 states a specific verb (返します/returns) and a precise resource: SealGate integration guide, enumerating its content topics (flow, REST API, browser SDK, server-side examples, errors, pricing) and the return format (Markdown). This clearly distinguishes it from siblings, which are data retrieval (get_app, list_*), action (issue_*, revoke_*), or utility tools.

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 states what the tool returns but gives no explicit when-to-use or when-not-to-use guidance. However, the tool takes zero parameters and returns static documentation, so the use case is largely self-evident, and none of the siblings overlap with guide retrieval, making confusion unlikely. Still, there's no explicit routing or exclusion language.

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=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds context about the API key requirement and the data scope, but it does not disclose details like output format, latency, or potential errors. This is acceptable given the strong annotation coverage.

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

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

A single compact sentence front-loads the return values and includes the key prerequisite without redundancy. Every phrase earns its place; no filler or repetition of schema annotations.

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 only one parameter and no output schema, the description adequately enumerates the returned metrics and their time windows. It is slightly ambiguous what 'ログイン成否' means precisely (e.g., counts vs. statuses), but overall a caller has enough context to invoke the tool and understand its result.

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 already documents api_key with format 'sk_live_…'. The description adds meaningful provenance by explaining that the key is issued from the admin screen (管理画面で発行したキー), which goes beyond the schema and helps the agent understand where to obtain the required parameter.

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 uses the specific verb '返します' and enumerates the exact metrics returned: MAU (6 months), completed registrations, login success/failure in the last 30 days, user count, and key types. This clearly identifies the resource and content, and distinguishes get_stats from sibling list/get tools that return records rather than aggregate metrics.

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 usage: call this tool when you need these aggregated statistics. It provides a prerequisite ('api_key が必要: 管理画面で発行したキー'), but it does not explicitly state when to prefer this over alternatives such as list_users or get_app, nor give any when-not-to-use 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?

The annotations provide no positive hints, so the description carries the burden. It does add useful context: the token expires in 15 minutes and an api_key is required. However, it does not disclose side effects such as whether issuing a new token invalidates previous recovery tokens, nor any failure/error 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?

Two compact sentences plus a parenthetical prerequisite. The purpose is front-loaded, and every sentence adds operational value without redundancy.

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

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

The description covers the use case, token validity, authentication requirement, and a prerequisite. With no output schema, the exact token response format is not specified, but the description provides enough for an agent to decide when and how to invoke the tool 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 67%: api_key and reason have schema descriptions, but external_id has none. The description reinforces the api_key requirement but does not clarify external_id semantics, so it only partially compensates for the missing parameter documentation.

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 identifies the operation: returning a 15-minute-valid recovery token for a user who lost their device and needs to re-register a passkey. This is specific enough to distinguish the tool from siblings like revoke_credential and revoke_user.

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 a precise when-to-use scenario (lost device, passkey re-registration) and an important prerequisite (developer-side identity verification must be completed first). It does not explicitly list when-not-to-use or alternative tools, but no closely competing sibling exists.

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 read-only, idempotent, and non-destructive behavior. The description adds useful context beyond that: results are returned newest-first, event and since act as filters, and api_key must be an admin-issued key. This is meaningful behavioral disclosure for an audit-read 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 description is one focused sentence with a short parenthetical. It front-loads the resource and ordering, then covers filters and auth requirements with no filler or repeated schema content.

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 read-only audit listing with fully documented parameters and safety annotations, the description covers purpose, ordering, filters, and authentication. The main omissions are explicit sibling differentiation and response-record shape, but no output schema exists and the operation is simple enough that these are not blocking.

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 event, limit, since, and api_key, including limit defaults and ISO 8601 format. The description adds only marginal meaning by grouping event and since as filters and noting api_key is admin-issued, which aligns with the high-coverage baseline of 3.

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—registration, login, revocation, and recovery records—and a specific behavior: return them in newest-first order. This is unambiguous and differentiates list_audit from sibling tools like list_users and list_credentials even without naming them.

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 provides clear usage context: retrieve auth-lifecycle audit records, optionally filtered by event and since, and requires an admin-issued api_key. It does not explicitly contrast with alternatives such as get_stats or get_app, so it stops short of full sibling 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?

Annotations already indicate a read-only, idempotent, non-destructive operation. The description adds meaningful behavior beyond that: the result includes revoked passkeys and distinguishes them by revoked_at, and it discloses an authentication requirement for api_key. No contradiction with annotations.

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 one compact, front-loaded sentence with a short parenthetical auth note. Every phrase contributes information: operation, resource, inclusion of revoked items, distinguishing field, and required key.

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

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

For a simple read-only list tool with two documented parameters, the description covers purpose, the revoked-inclusion caveat, the distinguishing field, and the auth requirement. There is no output schema, but the description gives enough expectation of the return shape without needing exhaustive detail.

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 both parameters are already fully documented. The description adds minimal extra context by tying external_id to '利用者' and clarifying that api_key is issued from the admin console, but it does not add significant 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?

The description states a specific verb and resource: returns a list of a user's passkeys (by external_id). It also distinguishes itself from siblings like list_users and revoke_credential by clearly scoping to passkeys and mentioning revoked_at.

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 clear context: use this to retrieve passkeys for a given external_id, noting that revoked passkeys are included and that an api_key from the admin console is required. It does not explicitly name alternatives or when-not-to-use cases, but the resource scope makes the intended use 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds domain semantics (tax exclusion and MAU-based banding) but does not disclose any additional behavioral traits such as authentication, rate limits, or response shape. No contradiction with annotations.

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 two short sentences with no filler. The core subject is front-loaded ('ステップ式の料金表 (税抜)'), and the second sentence adds necessary pricing context without redundancy.

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

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

For a zero-parameter, read-only list tool, the description and annotations cover safety and the essential pricing semantics. It is slightly incomplete in that it does not indicate what fields the returned pricing table contains, but the low complexity and clear subject make it adequate.

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 has zero parameters, so there is nothing for the description to document beyond what the schema already provides. A baseline of 4 is appropriate because no parameter ambiguity exists.

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 identifies the resource as a step-based pricing table (tax-excluded) and distinguishes it from sibling tools like list_users or list_credentials by its subject matter. It lacks an explicit verb such as '取得する' or '一覧表示する', so it is clear but not a fully specified action statement.

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

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

No explicit guidance is given about when to call this tool versus alternatives, and no when-not-to-use conditions are provided. The description explains how pricing works (MAU bands determine the monthly fee), which is useful context, but it never states the intended invocation scenario.

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 read-only, idempotent, and non-destructive behavior. The description adds the auth requirement, the q filtering behavior, and the exact returned fields, which goes beyond the structured metadata.

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 compact and well-ordered: purpose first, then filtering, then auth. Every clause earns its place with no redundant wording.

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

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

For a simple read-only list with three parameters and no output schema, it covers returned fields, filtering, and auth. It could mention limit/pagination behavior more explicitly, but the schema already documents the default, making this a minor 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 100%, so api_key, q, and limit are already documented in the schema. The description restates the q filter and api_key requirement, adding only the minor extra context that the key is issued from the admin screen.

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 uses a specific verb and identifies the exact resource: passkey-registered users, with the returned fields enumerated. This clearly differentiates it from sibling tools like list_credentials and revoke_user.

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 clearly states what the tool does and that an admin-issued api_key is required. It does not explicitly mention alternatives or when not to use this tool, but the context is strong enough for basic 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?

The description explicitly warns '取り消せません' (cannot be undone), reinforcing the destructiveHint annotation with a qualitative consequence. It also adds that the api_key must be issued from the admin console, which is useful auth context beyond the schema and annotations. No contradiction with the annotations was found.

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

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

Two short sentences front-load the action, immediately flag irreversibility, and state the auth requirement. There is no fluff or redundant restating of schema fields.

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 destructive tool with 100% schema coverage and relevant annotations, the description captures the essential action, consequence, and auth need. It does not mention what happens to the associated user or how to locate the credential_id, but those gaps are minor at this complexity level.

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 applies: the schema already defines api_key and credential_id clearly. The description adds only minimal provenance for api_key ('管理画面で発行したキー') and does not meaningfully expand on credential_id 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?

The description states a clear verb and resource: 'パスキーを1本失効します' (revoke one passkey), and the singular '1本' makes the granularity clear. It does not explicitly contrast itself with sibling tools like revoke_user, but the resource type is specific enough to avoid obvious confusion.

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 about when to use this tool versus revoke_user, issue_recovery_token, or list_credentials. The mention that an api_key is required is an authentication prerequisite, not a usage context or alternative-selection rule.

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 signal destructiveness and idempotency; the description adds valuable context by stating the operation is irreversible ('取り消せません') and requires an admin-issued api_key. No contradiction with annotations.

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 one compact sentence that front-loads the operation and scope, then adds the critical trigger, irreversibility warning, and auth requirement. Every clause earns its place with no filler.

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

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

For a destructive two-parameter tool with no output schema, the description covers trigger, scope, irreversibility, and auth. It does not explicitly describe the post-condition (e.g., the user can no longer authenticate with those passkeys), but that is reasonably implied by '失効'.

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 50% (api_key is described in the schema, external_id is not). The description compensates by clarifying that external_id identifies the user and that api_key must be issued from the admin console, though it does not specify external_id's format.

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 action ('失効します' — revoke) against a specific resource ('利用者 (external_id) のパスキーをすべて' — all passkeys of the user). It also differentiates from the sibling revoke_credential by emphasizing 'すべて' (all), making the user-level scope explicit.

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 explicitly gives the intended use cases ('退会・乗っ取り時' — for account deletion or takeover) and the required api_key from the admin console. It does not explicitly mention when not to use it or contrast it with revoke_credential, so it stops short of 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 mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context beyond that: registration must be performed by the user personally with Google or GitHub, the agent cannot proxy the registration, and the API key issued later should be passed to future tools. This is genuinely useful operational information.

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 concise sentences with no filler. The primary result is front-loaded in the first sentence, and the second sentence carries the key constraints and follow-up 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?

For a zero-parameter, read-only informational tool with no output schema, the description is complete: it says what is returned, who must perform the registration, why the agent cannot do it, and what to do after registration. Nothing an agent needs in order to use this 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?

The tool has zero parameters and the schema covers this fully, so the baseline is 4. The description adds value by explaining that the API key obtained after registration should be used as the api_key argument for subsequent tools, which clarifies the workflow without needing any parameter documentation.

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 and resource: 'SealGate の登録 URL を返します' (returns the SealGate signup URL). It clearly distinguishes itself from the sibling tools, none of which handle registration, and the title reinforces the purpose without being the only source.

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 tells when to use the tool: when the user needs to register for SealGate. It also provides an important exclusion: the agent cannot register on the user's behalf, so the tool should only be used to give the user the signup URL. It does not name an alternative tool, but no closer alternative exists among the siblings.

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