xonta-docs

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

Annotations already declare readOnly/idempotent/closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: VAT can be either included in or added on top of the amount, and currency coverage is limited to RUB/USD/EUR/CNY. It does not mention limits or edge cases (e.g. negative or zero amounts), so not 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 concrete output example, then the VAT behavior, then currencies — a sensible order with no filler. The final English sentence duplicates the opening Russian one, which is mild redundancy rather than waste.

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

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

There is no output schema, yet the description supplies two literal example strings including the generated VAT clause, so the agent knows exactly what comes back. For a 5-parameter, single-purpose formatting tool this is sufficient to call it correctly.

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

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

Schema coverage is 100%, so baseline is 3, and the description genuinely adds meaning: it explains vat_included as 'в том числе или сверху' and pairs the VAT-rate concept with a produced output line. That clarifies the interplay between vat_rate and vat_included better than the schema alone, though it still does not document the kopecks enum values.

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?

Names a specific transformation (amount → words) plus the concrete artifact it produces for invoices/acts/contracts, with a worked example. Nothing in the sibling set (decline_name, validate_requisites, working_days) overlaps, so an agent can route correctly without ambiguity.

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?

States the context of use explicitly ('для счетов, актов и договоров') and notes the VAT-line scenario, which is clear guidance on when this tool applies. It stops short of naming when NOT to use it or pointing to an alternative, since none of the siblings compete here.

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

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

Annotations already declare readOnlyHint, idempotentHint and closed-world, so safety is covered. The description adds genuinely non-structured behavior: it auto-detects gender from patronymic or first name, and it returns the full declined form plus initials — useful output-shape context absent from the schema.

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

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

Front-loaded with the core action, then examples, then behavioral notes, with an English gloss at the end. The inline examples are informative rather than padding; the only mild redundancy is repeating the action in English after the Russian.

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 8 optional parameters and no output schema, the description compensates by describing what comes back (full form and initials) and how gender and case=all behave. Remaining gap is the relationship between full_name and the split last/first/middle_name parameters, which only the schema covers.

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 baseline is 3. The description goes beyond it by mapping the 'all' value of case (all six cases at once) and by explaining the gender-inference fallback, which clarifies why the gender parameter exists only as a backup.

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: declines Russian full names and job titles by grammatical case. The concrete examples («в лице генерального директора Иванова Ивана Петровича») make the output shape unmistakable and clearly distinguish it from siblings like amount_in_words or validate_requisites.

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

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

Names the document contexts where it applies (contracts, powers of attorney, orders) and explains the case=all shortcut for retrieving all six cases at once. It does not explicitly state when to avoid it or name an alternative, but the domain of use is clear from the examples.

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

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

Annotations already establish readOnly/idempotent/closed-world, so the safety profile is covered. The description adds genuine behavior not in the annotations: the validation is offline and instant, and it flags when the supplied identifiers look like they belong to different persons/entities. It stops short of describing partial-input behavior or the exact response shape.

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

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

Front-loaded with the core action and the identifier list, then the payoff (catching typos) and the key property (offline, instant). It is slightly redundant because the same content is given twice in Russian and English, but each version is tight and waste-free.

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 7-parameter, all-optional, no-output-schema tool, the description covers purpose, the identifier set, and even one aspect of the result (mismatched-persons warning). The remaining gap is that it never clarifies that zero required parameters means partial sets are acceptable and what is reported per field.

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% and each parameter already carries its own Russian description with digit counts, so the description's digit hints largely duplicate the schema. No additional semantics (e.g. which combinations are meaningful, or behavior when only some fields are supplied) are added beyond what the schema 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?

States a specific verb (проверяет/validates) and an explicit, enumerated resource set (ИНН, КПП, ОГРН/ОГРНИП, БИК, расчётный/корреспондентский счёт, СНИЛС), including the checksum method. Nothing among the siblings (amount_in_words, decline_name, working_days) overlaps, so the agent can select this unambiguously.

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

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

Gives a clear use context — catching typos before issuing an invoice or payment ("до выставления счёта или платежа") — which tells the agent when to reach for it. It does not name any alternative tool or state exclusions, but no sibling competes for this job.

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 openWorldHint=false, so the safety profile is covered. The description adds that the data is the official RF calendar with holidays and transfers, but omits coverage years/freshness and any note on whether the calendar is bundled or remote, so beyond the mode mechanics it contributes modestly.

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 resource statement, then a cleanly numbered three-mode list; every clause carries information an agent needs. The only mild redundancy is the bilingual English restatement at the end, which duplicates the opening rather than adding 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?

With no output schema, the description does describe what each mode returns (a resulting date, a count of days and hours, a day classification plus next working day). It stops short of stating the response shape or the calendar's year coverage, which an agent might need for edge dates outside the supported range.

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 defining the meaning of parameter combinations rather than individual fields — which pair triggers addition, counting, or classification. It does not restate format details already in the schema, which 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?

Names the specific resource (Russian production calendar with official holidays and transfers) and enumerates exactly what the tool computes in each of its three modes. Sibling tools (amount_in_words, decline_name, validate_requisites) are in unrelated domains, so no disambiguation is needed and none is attempted.

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?

Explicitly maps each parameter combination to a distinct use case: date + add_working_days for deadline arithmetic, date + end_date for day/hour counting, and date alone for weekday/holiday classification. It even frames a real scenario ("оплата в течение 5 рабочих дней"), leaving no inference about when to pick a mode.

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