Tizona — Australian business identity tools

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

With no annotations and no output schema, the description carries the behavioral burden. It discloses the integer-cents rounding guarantee and calls out the common one-eleventh vs one-tenth error for inclusive amounts, which is genuinely useful behavioral information. It could go further by stating exactly what the return value is, but the core calculation behavior is well covered.

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

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

The description is compact and front-loaded, with the primary operations stated immediately. The warning about the one-eleventh rule is relevant, earned its place, and does not obscure the essential guidance.

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 is complete for the intended operation: it identifies the input modes, explains the calculation behavior, and warns about the key error mode. The slight gap is that it does not explicitly state the output shape or return type, which would be more important if there were no output schema, but the tool is simple enough that this is a minor issue.

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

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

The schema already describes both parameters well: amount is a money string with at most two decimal places and basis is an enum with descriptions. The description does add useful calculation context, but it does not significantly extend the parameter semantics beyond the schema's explanations.

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

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

The description names a specific operation and resource: calculate Australian GST. It uses concrete verbs ('Add GST', 'extract the GST') and clearly identifies both supported computation directions. This is sufficiently precise to distinguish it from the unrelated entity matching and sanctions sibling 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 clearly tells the caller when to use each mode: for GST-exclusive amounts, add GST; for GST-inclusive amounts, extract the GST component. It does not explicitly exclude alternatives like total_invoice, but the use-case framing is concrete and actionable enough to guide correct selection.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by explaining the tool's handling of legal forms, word order, generic words, and obfuscation, including the 'obfuscation' field in the response. It also warns about the 'distinctiveness' figure, which is a behavioral nuance. However, it does not mention any potential side effects, rate limits, or error conditions, but for a read-only comparison tool, this is acceptable.

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 well-structured and front-loaded with the core purpose. It is concise but includes necessary details about edge cases and the 'distinctiveness' warning. The only minor issue is that the second paragraph about obfuscation could be slightly more concise, but it is still valuable information.

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

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

Given the tool's complexity (handling legal forms, obfuscation, distinctiveness) and the lack of an output schema, the description is quite complete. It explains the output format (score, reasoning, obfuscation field) and the 'distinctiveness' figure. It could be improved by mentioning the exact structure of the reasoning output, but the description is sufficient for an agent to call 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?

The schema description coverage is 100%, so the schema already documents all three parameters. The description adds value by explaining the semantics of the 'type' parameter (defaults to company) and the behavior of the 'a' and 'b' parameters (e.g., word order ignored). However, it does not add much beyond the schema, so a baseline of 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?

The description clearly states the tool's purpose: scoring whether two names refer to the same entity, with a specific output range (0 to 1) and reasoning. It distinguishes itself from siblings like 'match_entity_name' and 'deduplicate_entity_names' by focusing on pairwise comparison and scoring, and it explicitly mentions the 'distinctiveness' figure, which is a unique feature.

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 context on when to use this tool: for comparing two names, with examples of what it handles (legal forms, word order, generic words). It does not explicitly state when not to use it or name alternatives, but the sibling list and the tool's specific focus imply its use case. It could be improved by explicitly contrasting with 'match_entity_name' or 'deduplicate_entity_names'.

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

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

With no annotations on the tool, the description carries the full burden, and it delivers: it discloses that grouping is heuristic rather than exhaustive, that the tool reports its own comparison count, and that the 'truncated' flag signals an unreliable result. It even explains what to do in that failure case. That's exactly the framing an agent needs to trust or doubt the output.

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, all dense with meaning. The core purpose lands in the verb and direct object, the second sentence explains the mechanics, and the third handles the critical edge case. There's no filler or repetition of the schema, and every clause in the final sentence earns its place in warning about the truncation caveat.

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 there's no output schema, the description does well to pre-empt the most confusing part of the response (the comparison count and the 'truncated' flag) and tells the agent what reaction is appropriate. It still stops short of a full description of the return shape and an explicit contrast with the comparison/sanctions siblings, both of which would round it out in a low-annotation context.

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?

With schema coverage at 33%, only `threshold` gets a schema description (its default), and the description only partially compensates. It implies that `names` is a list of entity names and ties the 250-cap to that parameter, but it never explains the `type` (company/person) parameter, which is an enum and likely affects matching behavior. The description earns credit for the grouping caveat, but the undocumented `type` param is a real gap.

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

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

The description leads with a specific verb and resource ('Group up to 250 names into clusters that appear to be the same entity') and grounds it in a concrete job ('CRM merge or a supplier list cleanup'). It also differentiates itself from siblings like normalise_entity_name and compare_entity_names by framing the output as clusters rather than a transformation or a pairwise verdict, so an agent can pick it apart from the alternatives.

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 context for when it should be used: batching many names and aggregating them into entity groups, and it offers an actionable when-not rule ('split the list and retry rather than reporting the result as final') for the truncation case. It never names any sibling tool, though, so an agent choosing between deduplicate_entity_names, compare_entity_names, and match_entity_name gets no explicit decision 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?

With no annotations provided, the description carries the full burden of conveying behavior, and it does so well: it discloses ranking, threshold filtering, and the position correlation mechanism. However, it doesn't mention potential side effects, score range, or error behavior, which is acceptable for a read-only matcher but leaves some gaps.

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

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

Two sentences of dense, front-loaded information. The first sentence covers the entire core functionality, and the second adds usage guidance with no 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 tool with no output schema, the description conveys the essential return value: filtered, ranked results with positions. It covers the main behavioral aspects an agent needs to call it correctly, though it could clarify the score domain (e.g., 0-1) and interaction between limit and threshold.

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 80%, so the baseline is 3. The description adds contextual meaning around candidates ('up to 750'), threshold ('above a threshold'), and positions in the input array, which helps an agent understand how parameters interrelate, but it doesn't clarify the missing 'type' parameter or score 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?

States a specific verb ('Score'), a resource ('one name against up to 750 candidates'), and a precise behavior (return above threshold, ranked, with array positions). Explicitly contrasts with pairwise comparison, distinguishing it from siblings like compare_entity_names.

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?

Provides a clear use case ('to find a customer in an existing list') and an explicit alternative ('rather than comparing pairs one at a time'). Could be stronger by naming the sibling tool, but the guidance is actionable.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It delivers on this by revealing that legal forms are separated out, every removed token is reported, and obfuscation is flagged. This goes well beyond a generic 'normalise' statement, though it stops short of describing the exact output structure or error conditions.

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 exactly two sentences with no wasted words. The core purpose is front-loaded in the first clause, followed by the two most important behavioral details (reporting removals, flagging obfuscation). Every element 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 transformation tool with no annotations and no output schema, the description covers purpose and key behaviors but omits the return format (how removals are reported, how obfuscation is flagged) and the semantic effect of the 'type' parameter. These gaps are material enough that an agent would need to probe or inspect siblings to use it confidently, but the core guidance is present.

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

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

Schema description coverage is only 50%, with the description of 'name' being tautological and 'type' having no description at all. The tool description adds some meaning to 'name' (reducing to core, separating legal form) but says nothing about the 'type' parameter, leaving the company/person distinction unexplained. It does not compensate for the schema gap.

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

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

The description states a specific verb ('Reduce'), resource ('a name'), and outcome ('to its comparable core with the legal form separated out'). The phrase 'stable grouping key' clarifies the transformation's intent and distinguishes it from sibling comparison/match tools without needing to open their schemas.

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 when-to-use context by positioning the tool as 'useful as a stable grouping key'. However, it does not explicitly state when not to use it or name alternatives like compare_entity_names or match_entity_name, so it falls 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?

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states what the tool reports and adds a meaningful caveat about the freshness field and its implication for screening results. It does not mention side effects or error conditions, but for a read-only reporting tool with no parameters, the transparency is strong.

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, each earning its place: the first states the function, the second gives the use case, and the third provides an important interpretive warning. No filler or repetition; the most critical information is front-loaded.

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, parameterless reporting tool, the description covers what it returns, when to use it, and a key caveat. It does not explicitly state that the operation is read-only or describe the exact output schema, but these are minor omissions given the tool's simplicity and the absence of an 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 tool has zero parameters and the schema is empty, so there is nothing to document. The description adds value by enumerating the output fields (source, publication date, hash, size, age) and the freshness field, which goes beyond the minimal schema. Baseline 4 is appropriate for a no-parameter tool.

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

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

The description opens with a specific verb and resource: 'Report the source, publication date, hash, size and age of the sanctions list currently in use.' It clearly distinguishes this from sibling screening tools by describing a metadata-reporting function rather than entity matching or screening. The auditor use case reinforces the purpose.

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 concrete trigger ('An auditor asks which list version a decision was made against') and provides a caution about checking freshness before relying on nil screening results. It does not explicitly name alternative tools or state when not to use this tool, but the context is clear enough for an agent to select it appropriately.

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

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

With no annotations present, the description carries the behavioral burden, and it does so well: it discloses fuzzy matching behavior, transliteration/obfuscation handling, the need for human review on a hit, and the fact that a nil result is not a clearance. It does not specify auth, rate limits, or the exact response shape, though 'Check whether' implies a non-mutating lookup.

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 the core function and then organized into purposeful blocks: scope, interpretation caveats, and common-name false positives. Every sentence adds compliance-relevant value, but the description is longer than strictly necessary and slightly repeats the scope point via 'OFAC SDN list ONLY' followed by the exclusion list.

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?

Since there is no output schema, the description usefully explains key result semantics: hits include a score and list publication date, and a nil result means no close name on that list. It also covers false-positive handling and common-name ambiguity. It lacks a precise output contract such as exact field names, empty-result shape, and error conditions, so an agent must still infer some response details.

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

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

The input schema has 100% parameter coverage, so the baseline is 3. The description adds useful color around `subject`—partial and reordered names, transliteration, obfuscation—and introduces the idea of a score, which relates to `threshold`. It does not meaningfully explain `includeWeak` or `type` beyond what the schema already states.

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 opens with a specific verb and resource: 'Check whether a person or company name appears on the OFAC Specially Designated Nationals list.' It further narrows scope by stating it covers only OFAC SDN and is not a UN/EU/UK/DFAT or PEP check. However, it never names or contrasts the sibling tools such as match_entity_name or sanctions_dataset_version, so sibling differentiation is implicit rather than 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 gives strong when/where context: it explicitly says the scope is OFAC SDN only, explicitly excludes UN/EU/UK/DFAT and PEP, and instructs the agent to state this to the user. It also tells the agent how to interpret hits and nil results to prevent compliance misuse. It stops short of naming alternative tools to use for excluded lists or for generic entity matching, so it lacks full when-not/alternatives 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?

There are no annotations, so the description carries the transparency burden. It clearly discloses the key behavior: the tool returns totals plus a comparison of per-line versus total-based rounding and the discrepancy, and explains why that discrepancy matters. It does not detail failure modes or side effects, but for a pure calculation tool the stated return behavior is the essential transparency.

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

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

Two sentences with no filler. The first sentence front-loads the operation and scope, and the second explains the non-obvious output and rationale. Every sentence 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?

The description covers purpose and high-level output, but with no output schema and no annotations it omits the exact return shape, any failure behavior, and how taxInclusive or quantity affect the totals. For a tool with three parameters and line-item complexity, a bit more detail would make it fully 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 of 3 applies. The description adds context for GST-free lines and both rounding methods, but it does not need to explain taxInclusive or quantity because the schema already describes them adequately.

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: 'Total a multi-line invoice, handling GST-free items and both permitted rounding methods.' It also distinguishes itself by saying it returns a comparison of per-line versus total-based rounding, which is not what the sibling tools like calculate_gst appear to do.

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 useful context about when the tool is relevant: multi-line Australian invoices with GST-free items and either permitted rounding method. However, it does not explicitly say when to prefer this tool over calculate_gst or other siblings, nor when not to use it.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses normalization behavior (spaces/hyphens ignored), the ABN company-reporting extra, the BSB no-check-digit limitation, and the important limitation that checksum validation does not prove an identifier is real. It does not mention the exact return format, but covers the main behavioral and limitation aspects well.

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 the core purpose in the first sentence, followed by a clearly labeled and essential caveat paragraph. Every sentence contributes useful information; the warning about not claiming an identifier is 'real' or 'registered' is justified and non-redundant.

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

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

The tool has no output schema, so the description should explain what the tool returns, but it only says it 'reports' validity and company status for ABNs. It does not specify whether the result is a boolean, an object with details, or how errors are represented. This is the main gap; otherwise the caveats and identifier coverage are thorough.

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

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

The schema already covers both parameters fully, including enums for type and a value description. The description adds non-obvious semantic context beyond the schema: that ABN validation additionally reports company status, and that BSBs only get format confirmation. This exceeds the baseline value expected when schema coverage is 100%.

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 precise verb ('check'), a resource ('Australian ABN, ACN, ARBN, TFN, Medicare card number or BSB'), and the method ('against its official checksum'). This clearly distinguishes it from the sibling tools, which concern entity names, GST, sanctions, and invoices.

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 context for when to use the tool and explicitly cautions against over-interpreting results: a passing checksum does not prove registration or issuance. It does not name sibling alternatives, but none of the listed siblings perform identifier checksum validation, so exclusion is implicit.

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