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

With no annotations, the description carries the full burden; it implies a read-only retrieval and discloses the shape of returned data (frequency, next date, annualized cost), which is genuinely useful. It does not state behavior on empty results (no subscriptions detected), detection criteria, or whether it covers all accounts.

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 that front-loads the resource and then the returned fields; every element 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?

An output schema exists, so the description needn't restate return structure, and it still briefly signals the headline fields. For a zero-parameter, read-only listing tool this is nearly complete; only detection scope and empty-result behavior are unaddressed.

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 takes zero parameters, so there is nothing for the description to disambiguate beyond the schema. Baseline 4 applies.

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

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

The description names the resource precisely (recurring charges / subscriptions) and enumerates the returned fields (amount, periodicity, next charge date, annual cost). It is clearly distinguishable from siblings like spending_by_category or forecast_month, though it opens with a noun phrase rather than an explicit verb.

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 on when to choose this tool over find_unusual_transactions, search_transactions, or forecast_month, and no stated preconditions (e.g. that a bank connection or transaction history is required). Usage is only implied by the resource name.

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 behavioral burden, and it does add real content by defining 'unusual' as above-normal for category plus possible double charges. It does not state that the tool is read-only, what threshold or heuristic defines 'usual', or whether results are ranked or capped. An output schema exists, so return shape needn't be explained, but the detection logic remains opaque.

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 with no filler or repetition, and the defining criteria are front-loaded. It is arguably too terse to be actionable, but that shortfall is a completeness problem rather than a verbosity one.

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 a non-trivial analytical purpose, one undocumented optional parameter, and no annotations, yet the description is one clause long. It should explain what makes a transaction 'unusual' (threshold, comparison period) and what `month` controls. The output schema covers return values, but essential call semantics are missing.

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

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

Schema description coverage is 0%, and the single `month` parameter appears nowhere in the description. An agent cannot tell from the text whether `month` scopes the analysis window, is required, or defaults to the current month (the schema only shows a null default). The description 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?

Names a specific capability: finding transactions that are unusually large for their category, plus possible duplicate charges. This is more informative than a generic 'find transactions', and it is implicitly distinct from search_transactions and spending_by_category. However, it never explicitly contrasts itself with siblings, so the differentiation is left to inference.

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 statement about when to use this tool vs. search_transactions, find_subscriptions, or forecast_month. The single sentence describes what the tool finds but gives no trigger conditions, prerequisites, or exclusions. An agent would have to guess when this tool is the right choice.

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, yet it never states that the tool is read-only / makes no changes, nor what it does if no statement is loaded. It does disclose the calculation basis ('at the current spending rate'), which is genuine behavioral context.

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

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

A single front-loaded sentence with no filler; the forecast horizon and basis both appear immediately.

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-param tool with no output schema, an agent still lacks two things: how 'the last statement month' is determined (implicit dependency on load_statement data) and what the returned forecast looks like. Otherwise 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?

Zero parameters, so there is nothing for the schema to document and no syntactic detail required. Baseline 4 applies; no parameter gaps exist to compensate for.

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 verb (forecast/prognosis) and resource (expenses) and bounds the horizon ('until the end of the last statement month at the current spending rate'). It is distinguishable from siblings like spending_by_category or search_transactions, though it never names an alternative explicitly.

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 statement of when to call this versus the six sibling tools (e.g. after load_statement, or instead of historical spending breakdowns). Usage is only inferable from the word 'forecast' itself.

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?

No annotations are provided, so the description carries the full disclosure burden. It only says the tool returns a period and totals; it omits whether the load is idempotent, whether it overwrites previously loaded data, what permissions or file-access constraints apply, and how malformed CSVs are handled.

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-loaded with the action and the accepted formats, with the return value last. Nothing is redundant, though the phrasing is terse to the point of under-specification.

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 one-parameter ingestion tool with no output schema and no annotations, the description covers purpose, accepted input shape, and a rough return summary. It still leaves the path semantics and the effect of loading on existing data unexplained, which matters for a mutation-style tool.

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 0% for the single required parameter 'path', which has no title or description beyond 'Path'. The description clarifies the file's expected content/columns but never explains whether 'path' is a local filesystem path, an absolute vs relative path, or something else — the one thing an agent must get right.

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+resource ('Загрузить выписку') and narrows the accepted input to a T-Bank CSV or a CSV with date/amount/description columns. That is enough to distinguish it from the sibling analytics tools (spending_by_category, forecast_month, etc.), which all operate on already-loaded data.

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 accepted file formats imply the tool is the data-ingestion entry point, but the description never says when to call it versus the siblings, whether it must be called before the analysis tools, or what happens if it is called repeatedly. No alternatives or exclusions are named.

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?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing about read-only safety, result ordering, default scoping across months, or pagination. 'Find' implies a read, but that must be guessed rather than stated.

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 front-loaded sentence with no filler. It is efficient but so terse that terseness shades into under-specification rather than genuine conciseness.

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

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

An output schema exists, so return values need not be explained, but for a 3-parameter search tool with no annotations the description leaves the month scoping, result limit behavior, and matching semantics undefined. It is not sufficient for an agent to invoke the tool correctly without trial and error.

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 0%, so the description should compensate, but it only clarifies the semantics of 'query' (description text or category name). The 'limit' and 'month' parameters are left completely unexplained in both schema and 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?

States a specific verb and resource ('Найти операции' – find transactions) and clarifies the two search dimensions: description text and category name. It is distinguishable from siblings like spending_by_category or top_merchants, though it doesn't explicitly say so.

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 by naming the two searchable fields, which tells the agent what kinds of queries work. However, it gives no explicit when-to-use vs. alternatives (e.g., spending_by_category for aggregates) and no exclusions or prerequisites.

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. It discloses useful behavior such as the default being the last month and that it reports month-over-month change, but it does not state read-only nature, permissions, or output 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?

The description is a single compact sentence that front-loads the purpose and includes the key parameter default and comparison behavior. Every phrase 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 simple one-parameter reporting tool with no output schema, the description gives enough to call it correctly and understand the return concept. It could be slightly richer about categories or the exact change metric, but the essentials are covered.

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 0%, so the description must compensate. It does: the single optional 'month' parameter is explained as YYYY-MM format with a default of the last month.

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 aggregation: spending broken down by category for a month, plus change versus the previous month. It is clearly distinct from siblings like top_merchants and search_transactions, though it does not explicitly name 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?

There is no explicit guidance on when to use this tool versus siblings such as top_merchants or search_transactions. Usage is only implied by the phrase 'расходы по категориям'.

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?

No annotations are provided, so the description carries the full behavioral burden. It does not disclose ordering (presumably descending by spend), what happens when month is omitted, or the fact this is a read-only aggregation — all relevant for a ranking tool whose date scope is implicit in 'за месяц'.

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 short sentence with zero padding, front-loading the resource and the ranking criterion. It is efficient, though it could have spent one more clause on routing or parameters without becoming bloated.

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

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

An output schema exists, so return values need not be described, but with no annotations and 0% schema coverage the two parameters are entirely unexplained in the definition. For a low-complexity aggregation tool this is the main missing piece and it is a significant one.

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 0%, so neither parameter is documented anywhere: 'n' has no meaning attached to it and 'month' has no stated format or default behavior. The phrase 'за месяц' hints that a month can be scoped, but gives no syntax to fill the 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 names a specific resource (merchants / shops and services) and a ranking criterion (most money spent in a month), which is enough for an agent to know what the tool returns. It does not explicitly contrast itself with the closest sibling spending_by_category, so the merchant-vs-category distinction is only inferable from the noun.

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 states what the tool shows but never says when to prefer it over spending_by_category, search_transactions, or find_subscriptions, and gives no prerequisites or exclusions. The agent must infer routing from the name alone.

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