MentionFox

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds value beyond them: cost ('about 5 credits a head, so a three-way is around 15'), free no-op when fewer than two people are on file, and free candidate listing on ambiguous names. These billing and failure semantics are exactly the non-obvious traits an agent needs before invoking.

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 action and is generally efficient, but the opening enumeration ('how they work, how they come across, where their careers have gone...') and the triple example ('candidates for a role, people to pitch, names on a shortlist') are stylistically redundant. Every sentence still carries information, so the verbosity is tolerable rather than wasteful.

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 tool with no output schema, the description supplies the return shape ('a table you can read down a column... or across a row'), cost, and failure modes, and the two parameters are fully covered by schema plus description. Nothing needed to invoke it correctly is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds framing semantics for 'context' ('Tell it what the comparison is for and the framing follows') and reinforces the 2-5 cardinality of 'people' beyond the schema's minItems/maxItems. It does not add syntax detail for name-vs-object forms, which the schema already carries.

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 ('compare people side-by-side') and specifies the comparison axes (how they work, careers, experience, visibility, connections). It also distinguishes itself from lookup siblings by stating 'It compares people you have already looked up,' which an agent can use to separate it from enrich_person or get_dossier without opening a schema.

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

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

Gives clear context for use ('candidates for a role, people to pitch, names on a shortlist') and a prerequisite ('people you have already looked up'), plus edge behavior for fewer than two matches. It stops short of naming which sibling to use instead when people are not yet on file, so routing is implied rather than explicit.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint). Beyond that the description adds genuinely useful billing behavior — 5 credits only on a hit, nothing charged for zero or multiple matches — and the disambiguation return path. It stops short of richer operational detail (latency, rate limits, what fields the candidate list 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?

Front-loads the return value, then usage triggers, then exclusions, then cost — a sensible ordering with no filler. It is on the long side for three parameters, but nearly every sentence carries a distinct fact.

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 exists, so the description carries the return-value burden and does so ('you get back the person, their current role, and the ways to contact them'), plus costs and the ambiguity branch. An agent has everything needed to call it and interpret the 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 coverage is 100%, so the baseline is 3, and the description earns one more by explaining the name-vs-employer interplay ('add their employer if the name is a common one') and the person_id lock-in flow implied by 'pick one and ask again' after disambiguation.

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 and resource: 'How to reach one person: their email address, phone number..., and their profile links.' It also explicitly carves itself out from the WHO-to-contact siblings ('this looks up somebody you can already name'), so an agent can separate it from find_buyers_now without opening a schema.

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

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

Gives concrete triggering utterances ('how do I get hold of her', 'find his email'), an explicit exclusion ('Do not use it to find out WHO to contact'), and the fallback workflow for ambiguous names (get candidate list, pick one, ask again).

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 declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, meaning this creates a persistent artifact. The description clarifies it makes a fixed copy and mentions cost (5 credits) and white-label branding, which adds value beyond annotations. However, it doesn't explain why it's destructive or whether exports can be overwritten/deleted, so with annotations already covering the safety profile, a 3 is appropriate.

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

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

The description is front-loaded with purpose and use cases, but it is somewhat verbose and includes multiple example phrases that could be condensed. Every sentence has some value, but the structure could be tighter.

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 tool with nested branding options, enum formats, and destructive annotations, the description covers purpose and some usage but omits details like credit cost implications on failure, handling of report_id for different types, or output structure. It's adequate but leaves clear gaps.

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

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

Schema coverage is 50%, so half the parameters are undocumented in the schema. The description mentions branding fields (logo, colours, name) and output formats implicitly, but doesn't explain the report_id variations for different report_types (e.g., person_profile_id for dossier). This gap is not fully compensated by the description.

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 tool converts existing content into a sendable file (web page, PDF, or plain text) with white-label branding. It conveys the core verb+resource but does not name or differentiate from siblings like get_snapshot or get_full_report.

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 trigger phrases ("send me that as a PDF", "I need this as a document for the client", "put our branding on it") and contrasts with sharing a live link. It doesn't name sibling tools or say when not to use this specific tool versus alternatives like get_snapshot.

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, but the description adds real behavioral value beyond them: cost of 1 credit only when results return, zero cost on empty results, a never-padded result list, US-only scope, and excluded filing categories. That is exactly the extra context an agent needs before spending credits.

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?

Dense and long, but every clause carries information: scope, exclusions, provenance fields, and billing rules are front-loaded. Only the free-trial URL and some prose flourishes could be trimmed without loss.

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 names the returned fields (record_url, why_now, fit, searched_feeds) and what their absence/short list means, so an agent knows exactly what a correct call yields. Nothing essential for invocation or interpretation is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description goes further by enumerating the event kinds (funding filings, new C-level, IPO, activist 5%+, layoffs, crowdfunding, YC) that map onto the trigger_types enum values and explaining that unspecified types default to a fitted selection. It does not clarify the 30/90-day option, but adds meaningful enum semantics.

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: takes your website, learns what you sell, and searches recent filings for up to 10 companies with a reason to buy. This is clearly distinguishable from siblings like enrich_person or get_dossier, which are not prospecting 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?

Explains the required input (your business website), the sourcing model, and constraints (US companies only, funds and real estate excluded, free trial link). It gives clear context for when the tool applies, though it never explicitly names a sibling tool to use instead for adjacent needs.

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

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

Annotations only cover the read-only/idempotent safety profile, and the description adds substantive behavior: 30-credit cost on first lookup, zero cost on cached lookups, no charge on ambiguous-name or no-match outcomes, and candidate-return semantics for ambiguous names. This is exactly the cost/ambiguity context an agent cannot infer from schema or 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?

Front-loaded with the payload description and use-case phrases before cost, which is the right order. Slightly bloated: the no-charge condition is restated three times ('nothing is charged ... nothing is charged when nobody matches') and the rhetorical 'the file, not the verdict' is decorative.

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 carries the burden of explaining what comes back, and it does so at the section level (activity, collaborators, mentions, writings, news) plus the summary/full distinction via the schema. It stops short of depth/volume expectations, but nothing required to invoke correctly is missing.

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

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

Schema coverage is 100%, with every parameter self-documented (including the refresh charge note and the name/person_id either-or constraint), so the baseline is 3. The description adds little parameter-level detail beyond echoing the cost model already stated in the 'refresh' schema field.

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

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

States a specific verb/resource ('everything on file about one person') and enumerates the returned sections—activity, collaborators, mentions, public statements, recent news. It also clears the field by naming what it is not ('this is the file, not the verdict') and what lighter siblings it competes with (brief, contact details).

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 concrete triggering utterances ('tell me everything about her', 'background on him before the call') plus explicit when-not guidance that routes to cheaper alternatives ('if you only need an email, ask for their contact details instead—that is far cheaper'; 'if a short written assessment is what you want, ask for a brief').

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 readOnlyHint=false and idempotentHint=false already set, the description goes well beyond the annotations: immutability after generation, free re-retrieval of a previously purchased report, separate billing for new_report, 50-credit cost, Pro-plan requirement, multi-minute latency with an async link fallback, and a name-collision flow that charges nothing. The remaining gap is that it never says what the returned artifact actually looks like structurally (format, delivery, size limits).

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, but the body is bloated: the credit cost is restated 24 times as '(50 credits)' in the subject_type list, and the immutability/caching idea is spread across three overlapping sentences. Several clauses restate what the new_report and company schema properties already say.

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 costly, non-idempotent generation tool with no output schema, the description covers pricing, plan gating, latency and async retrieval, caching semantics, disambiguation fallback, and the full accepted subject_type set — everything an agent needs to invoke 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 coverage is 100%, so the baseline would be 3, but the schema explicitly defers to the description for subject_type ('listed in this tool's description') and there are zero enums in the schema — so the 24-value subject_type list here is the only place an agent can learn valid inputs. It also adds the concrete company/website disambiguation example, giving real value over the schema text.

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 opening sentence gives a specific verb and resource — 'a full written report on one subject, section by section, ending with the sources it drew on' — and immediately scopes it against 'the short brief', which lets an agent separate it from the lighter snapshot/dossier siblings 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?

Explicit trigger phrases are supplied ('I need the full write-up', 'proper due diligence before we commit', 'the long one') plus an explicit contrast with the shorter tool, and the new_report flow spells out exactly when to re-request versus accept the cached copy.

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, non-destructive and closed-world, so the safety profile is handled. The description adds real context those annotations cannot convey: this call is free, nothing is looked up, no charge is incurred, and results are restricted to the caller's own history — the cost/scope model that actually determines whether an agent should call it.

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 well with the core answer in the first sentence, but it repeats the same idea twice: "Free: nothing is charged" and again "Nothing is looked up and nothing is charged." The duplication and the triple example-query list pad a description that could be half as long.

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, no-required-param history listing, the description covers what comes back (people, write-ups, calls) and the cost/scope boundary. It is only short on the mechanics of `limit` and any ordering/pagination note, which leaves a small gap given there is no output schema.

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

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

The single parameter `limit` has 0% schema description coverage — no description, no stated default or max in the schema text — and the description never mentions it at all. With low coverage the description is supposed to compensate, and it does not, so paging/result-size behavior is undocumented.

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

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

States a concrete verb ("Lists") and resource (people you researched, write-ups made, calls run) and pins the scope hard: "yours only, nobody else's." That scope plus "what you have already looked up" cleanly separates it from the research/enrichment siblings like enrich_person and get_dossier without needing to name 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?

Gives an explicit trigger ("Worth calling before you pay for something") and three sample user intents ("have I checked this person before", "what did I look at last week", "show me what I have"). It never names a specific alternative tool or a when-not case, 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?

Goes well past the annotations by disclosing per-type credit costs, the cache rule (the same subject asked twice is free and unchanged), the no-charge conditions (no such subject, or too little on the record), and the fact that new_report writes and charges for a second brief. This is exactly the pricing/side-effect context that readOnlyHint=false and idempotentHint=false hint at but do not explain.

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 deliverable, then usage, then cost/caching rules — every sentence carries information. The 23-entry price list is bulky, but it substitutes for the missing enum in the schema, so it earns its space.

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

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

For a paid, open-world lookup with no output schema, the description covers cost, caching, failure/refund conditions, what the returned page contains, and how to size the request (subject + subject_type). Nothing an agent needs before calling 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 baseline is 3, but the description adds meaning the schema lacks: the full subject_type vocabulary with per-type prices, plus the note that names should be qualified with employer/domain when ambiguous. It does not add much to new_report beyond the schema's own wording.

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

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

States a concrete deliverable (a one-page brief on a single subject) and its return shape (text plus a shareable link), then explicitly names get_full_report as the long-form alternative. An agent can distinguish it from get_dossier, get_full_report, and enrich_person without opening another 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 trigger phrasings ('who is this', 'quick read on this firm') and an explicit alternative ('For the long version, use get_full_report'). It also constrains which subject_type values are legal and notes they must match the live price list exactly.

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 (readOnly, openWorld, non-destructive). The description adds genuinely useful context the annotations cannot: a credit cost model (3 credits per source, ~15 for a default run) and the default breadth of ~55 platforms. It omits rate limits and any throttling behavior, keeping it short of 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?

Front-loaded with the core purpose and output shape, then usage examples, then exclusions and cost. It is wordy in places (a long output-shape clause), but with no output schema each of those clauses earns its place by describing what comes back.

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 adequately substitutes by enumerating return fields (source, link, sentiment, buying intent). Cost, default scope and the person-profiling exclusion round it out. Minor flaw: it says '55 places' while the schema says '50+', a small internal inconsistency.

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 67%, above the threshold where the schema carries most of the load. The description explains that sources default to all places and can be narrowed, and frames hours_back as 'the last day', but adds no format details and never addresses the 1-24 hour range enforced in 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+resource: scans for mentions of a named brand/product/topic/person and returns posts, comments, articles and videos with source, link, sentiment and buying-intent flags. It also distinguishes itself from siblings by declaring it does NOT build a picture of a person ('for that, ask for a brief'), separating it from get_dossier/enrich_person.

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 concrete when-to-use phrasings ('what are people saying about us today', 'did anyone pick up the launch') and one clear exclusion (person profiling). The alternative is only gestured at as 'ask for a brief', not named as a sibling tool, so routing is implied rather than explicit.

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

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

Adds substantial context beyond annotations: the four possible verdicts, the itemized output shape, the epistemic caveat that 'could not verify' is not evidence of fraud, the immutability of each result ('checking again later produces a new one and leaves the first alone'), plus cost (25 credits) and latency (a few seconds). The immutability statement is consistent with idempotentHint=false and explains why readOnlyHint is false, so there is no contradiction.

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 purpose, then output format, then caveats, then use cases and cost — a logical order with no filler. It is on the long side, and the 'It will never tell you somebody is fake' passage spends several sentences on one point, but the content is substantive rather than 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 no output schema, the description carries the return-value burden and does so fully: the four verdict types, per-claim confirmation with source links, explicitly empty searches, and a list of what was never checked. Cost and turnaround are also covered, so an agent has everything needed to call and interpret it.

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 already 100%, so the baseline is 3, but the description adds real meaning: 'Paste whatever you have — the pitch email, a name, a link — and the claims are read out of it', clarifying that the free-text input is parsed rather than matched verbatim. It doesn't discuss how the optional name/title/employer overrides interact with extraction, leaving a small 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?

States a specific verb and resource: it 'checks those particular claims against the official lists that would record them', with concrete claim types (doctor, lawyer, broker, professor, director). An agent can immediately tell this is a credential-verification tool, distinct from siblings like enrich_person or get_dossier that assemble profiles rather than test claims.

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 when-to-use triggers in quotes ('is this person who they say they are', 'check this expert before I quote them', 'is this doctor actually registered') and an implicit boundary via 'It will never tell you somebody is fake.' It does not name sibling tools as alternatives for adjacent needs, 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.