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

No annotations are provided, and the description does not mention whether the operation is read-only, what the result format is (e.g., list of callees), or any permissions or side effects. The agent is left without essential behavioral context beyond the core action.

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 very brief and to the point. It includes a necessary example, which adds value without unnecessary verbosity. The structure is clean, though the lack of an explicit command verb in English might reduce universal clarity.

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 simplicity, the description is minimal and lacks crucial context such as the expected return value (e.g., a list of call sites or function names) and any caveats. It is not sufficiently complete for an agent to fully anticipate the tool's behavior and output.

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 sole parameter 'full_name' has no schema description, but the description provides an example value ('ОбщийМодуль.МойМодуль.ИмяФункции'), which clarifies the expected format. However, it does not explicitly define what the parameter represents (the fully qualified name of the function) or any constraints.

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 'Кого вызывает функция' explicitly states that the tool returns the outgoing calls (callees) of a function. It clearly identifies the action (вызывает) and the resource (function), and contrasts with the sibling 'bsl_callers' by specifying 'outgoing calls'.

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 purpose is inherently clear from the name and description, but it does not explicitly instruct when to use this tool over 'bsl_callers' or other siblings. The distinction is implied rather than stated, which leaves some ambiguity for an agent.

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 must disclose behavioral traits. It only states the tool's purpose and gives a parameter example, with no mention of side effects, read-only nature, performance, or prerequisites. For a query tool, this is a notable gap.

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, efficient sentence that includes both the purpose and the parameter format. No wasted words, and the key 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?

The tool has a single parameter, an output schema (which covers return values), and a straightforward purpose. The description provides the essential parameter format. However, it does not mention any prerequisites (e.g., indexing via bsl_reindex) or caveats, but for a simple query tool this is acceptable.

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 provides a concrete example format for full_name ('ОбщийМодуль.МойМодуль.ИмяФункции'), which clarifies the expected structure beyond the bare schema. This adds meaningful guidance.

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

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

The description states a clear purpose: finding who calls a function (incoming calls). The example format for full_name adds specificity. The tool name and description implicitly differentiate it from bsl_callees (outgoing calls).

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 for finding callers, contrasting with bsl_callees for callees, but does not explicitly state when to use this tool over alternatives. The context is clear enough for an agent to infer, but a direct mention would strengthen 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, the description must disclose behavior. It explains the metrics computed and the filtering behavior, but does not explicitly state that it is read-only or describe error handling. The note 'Метрика ревьюеру' implies a read-only analysis role, but this is not explicit.

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 concise, with the purpose stated in the first sentence and parameter guidance in the second. The structure is clear and front-loaded, avoiding unnecessary verbosity.

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 adequately covers the required and optional parameters, and the output schema exists to define the return value. For a focused analysis tool, this is sufficient for an agent to call it correctly, though it could mention edge cases like non-existent module names.

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 description adds meaning to both parameters: it provides an example format for module_full_name ('ОбщийМодуль.МойМодуль') and clarifies that function is optional and restricts the analysis to a single method. This compensates for the 0% schema description coverage.

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 computes cognitive and cyclomatic complexity for module methods, a specific metric for reviewers. This distinguishes it from sibling tools like bsl_callers and bsl_references which focus on call graphs and definitions.

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 usage hints by explaining the module_full_name format and the optional function filter, but does not explicitly compare to alternatives or state when to prefer this tool over siblings. It implies usage for complexity analysis but lacks explicit guidance on 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure and delivers almost none. It says nothing about whether the lookup is read-only, how it resolves ambiguous or missing symbols, or what scope (workspace vs. index) is searched. An output schema exists, which mitigates the return-value gap slightly, but the operational behavior is undisclosed.

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 terse sentences: the purpose first, then the parameter format. No filler, and the most important 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 single-parameter lookup with an output schema, the description plus schema is minimally sufficient to invoke the tool. It falls short on routing guidance among five similarly named BSL siblings, which is the main way an agent would mis-select this 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% — the schema only labels the field 'Full Name' with no format detail — so the description's concrete example, 'ОбщийМодуль.МойМодуль.ИмяФункции', is the sole source of meaning for how full_name must be composed. That is genuinely valuable, though it covers only the dotted-path form and not edge cases like nested or exported methods.

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 lookup task — locating where a method is declared — which is a clear verb+resource and implicitly distinct from siblings like bsl_references (usages) and bsl_callers (call sites). It does not, however, name any sibling explicitly, so differentiation is left to inference from the tool names alone.

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 use this tool versus bsl_references, bsl_callers, or bsl_callees, all of which involve related BSL symbol queries. The agent must guess from the tool name whether this returns a declaration site or a usage site.

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 and does so thoroughly: it discloses default severity filtering, suppressed diagnostics summary, output shape, special cases for code/min_severity, and execution queue behavior. It also explains that checks are per-file without configuration 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?

The description is densely informative and well structured, with addressing modes first and behavior details second. Every sentence adds useful operational or filtering information, and the formatting keeps it scannable.

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?

Despite having no output schema and no annotations, the description fully covers input constraints, default behavior, output structure, filtering options, and performance-related context. It is complete enough for an agent to use 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 has zero description coverage, but the tool description compensates by explaining each addressing mode: module_full_name format, path scope, text snippet requirements, and the meaning of code and min_severity filters. This makes the parameters significantly clearer than the bare schema.

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

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

The description clearly identifies the tool as code diagnostics ('Диагностики кода') and explains it lints 1C code with different input modes. It is clearly distinct from sibling navigation, complexity, and reindex 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 provides clear usage context: exactly one of module_full_name, path, or text must be supplied, and it explains default severity behavior and per-file scope. It does not explicitly name sibling alternatives, but the context is strong enough to guide 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?

No annotations are provided, so the description carries the full behavioral burden, and it delivers almost nothing: no indication of search scope (project-wide vs. file), whether results depend on an index, whether it is read-only, or how many references are returned. Only the output schema hints at results.

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 with the purpose front-loaded and no filler. It is terse rather than bloated, though the extreme brevity borders on under-specification for a lookup tool.

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. For a 1-parameter read tool the description is minimally viable, but with no annotations it should say more about scope and indexing prerequisites.

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, and it does provide a concrete format example ('ОбщийМодуль.МойМодуль.ИмяФункции') that the schema lacks. However, it gives only a single example with no explanation of the dotted-path convention or edge cases, so the compensation is partial.

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 purpose — finding where a BSL method is used — with the resource (method) clearly identifiable. It does not differentiate from the near-synonym sibling bsl_callers, which an agent would need to distinguish (references vs. callers), so it stops short of a 5.

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 use this tool versus bsl_callers, bsl_definition, or bsl_callees, and no prerequisites (e.g. whether the project must be indexed). Usage context is only implied by the verb.

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 burden of behavioral disclosure. The description only says it performs a full reindex and is intended for large changes. It does not disclose potential side effects (e.g., whether it overwrites existing indexes, how long it takes, whether it requires special permissions, or whether it is safe to run concurrently). For a mutation operation, this is a significant transparency gap.

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

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

The description is two concise sentences, with the primary purpose front-loaded in the first sentence. The second sentence adds a useful clarification about when not to use it. No fluff or redundant phrasing. It could be slightly more structured (e.g., a bulleted list) but is efficient as-is.

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 no-parameter, no-output-schema tool, the description adequately explains what it does and when to use it. However, it omits details about the outcome or effects of the reindex (e.g., whether it returns a success/failure status, whether it blocks other operations, or any post-condition). Given that it is a mutation tool, some note about its runtime behavior or reversibility would improve completeness.

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 with 100% coverage by definition. Per the rubric, a zero-parameter tool receives a baseline of 4. The description adds no parameter-specific information (there is none to add) but also does not need to. It correctly focuses on the action and its intended use case.

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 a specific action (full reindex) on a specific resource (corpus) and gives the condition under which it applies (after mass configuration changes). This distinguishes it from the sibling tools, which all focus on analysis (callers, callees, definitions, references, diagnostics, complexity) rather than maintenance. The verb 'reindex' and resource 'corpus' are explicit and unambiguous.

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

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

The description provides clear usage context: use for large configuration changes, not for small module edits, which are handled automatically. It doesn't name alternative tools explicitly, but it gives a practical decision rule (mass vs. point changes). This is more specific than just 'when to use' and helps an agent avoid unnecessary reindexing.

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