Krasoft Russian Public Procurement

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

Annotations declare readOnlyHint=true, confirming no side effects. The description adds critical behavioral details: quota limits per account type and that exceeding returns isError with instructions. This goes beyond 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?

The description is concise with front-loaded purpose. The quota information is necessary but slightly extends length. Overall efficient with no wasted words.

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 no output schema, the description adequately outlines return content (name, region, stats, structure, suppliers) and error handling. It is complete for a simple tool with one parameter.

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 fully describes the 'inn' parameter with pattern and description. The description mentions INN but adds no further semantic meaning beyond the schema. Baseline 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 it provides a public customer profile by INN with specific fields (name, region, procurement stats, structure, suppliers). It distinguishes from sibling tools like 'get_contract' or 'search_tenders' by focusing on a consolidated profile for quick assessment.

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 explicitly says 'Suitable for quick assessment who is this and how much do they buy', which indicates appropriate usage. However, it does not explicitly mention when not to use or compare with alternatives, though the sibling list provides implicit differentiation.

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; description adds quota context and error response (isError with instructions). This goes beyond annotations, providing actionable behavioral details.

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?

Single paragraph, front-loaded with purpose, includes quota and error info. Every sentence contributes meaning. 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?

No output schema exists, but description lists all return KPIs. It also states what is not returned (list of positions). Quota limits and error behavior are covered. Adequate for a summarization 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 coverage is 100%, so baseline is 3. Description adds value by explaining that 'query' searches both position and contract text, and 'period' options with defaults. This enriches schema descriptions.

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?

Description clearly states it provides an aggregated KPI summary (totalSum, totalQty, totalPaid, contracts, suppliers) under a filter. Distinguishes from siblings by noting it does not return a list of positions, only KPIs. Specific verb+resource with clear scope.

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?

Description indicates suitability for assessing market volume and supplier share. Provides quota details for different account types and error behavior when quota exceeded. However, it does not explicitly state when not to use this tool versus alternatives.

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?

The description adds significant behavioral context beyond annotations: maskings on free tiers, daily quotas per account type, and error handling on quota exceed. This helps the agent anticipate outcomes, even though annotations already mark it readOnly.

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 content, then addresses limitations and quotas. It is reasonably concise with no fluff, though slightly longer due to quota details. Structure is logical.

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 the key aspects: what data is returned, limitations (free tier masking), and quota boundaries. With no output schema, this level of detail is sufficient for agent decision-making. No missing critical 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?

Schema coverage is 100% for the single parameter 'uniqId', which is already documented. The description reinforces its meaning but adds no new parameter details beyond what the schema provides. Baseline score 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 retrieves a contract card by internal ID, listing header and specification fields. However, it does not explicitly differentiate from sibling tools like get_tender or search_contract_specs, so it misses a clear distinction.

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 when to use (by providing the contract internal ID) but does not specify when not to use or mention alternatives. Quota information helps the agent assess feasibility, but no explicit guidance on avoiding overuse.

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. The description adds valuable behavioral context: quota limits per account type, error response when limits are exceeded, and what data fields are returned. No contradictions with 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?

The description is concise and well-structured: purpose first, then details, then quota info. Every sentence adds necessary information without 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?

Given the tool's simplicity (one parameter, read-only, no output schema), the description covers all relevant aspects: what it returns, how to get the ID, quota limits, and error handling. It is fully complete for the agent to use 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% and already describes the uniqId parameter as 'Внутренний ID извещения (ntfUniqID из search_tenders)'. The description repeats this information without adding new semantics, so it meets the baseline for high 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 that this tool returns a detailed card of a procurement notice by internal ID, listing specific fields (subject, conditions, customer, NMCC, stages, etc.). It explicitly links to search_tenders as the source of the ID, distinguishing it from sibling tools like search_tenders which return lists.

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 the ntfUniqID from search_tenders. It also details quota limits for different account types and error behavior when exceeded. However, it does not explicitly mention when not to use this tool or alternative tools, though siblings are listed separately.

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. Description adds quota details (20/50 for anonymous, 100/200 for free, unlimited for paid) and error behavior on quota exceedance, providing clear behavioral context beyond 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?

Multiple sentences but each adds substantive info; front-loaded with core purpose. Slightly verbose with quota details but well-organized. Could be more concise, but not 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 2-param tool with no output schema, the description fully covers what the tool does, what it returns, what it doesn't (prices), and usage constraints (quotas). No gaps given complexity.

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 descriptions. Description adds value by explaining the meaning of each 'kind' value and providing concrete examples (e.g., '21.20.10' for OKPD2, 'ibuprofen' for MNN slug).

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?

Clearly states it returns aggregated market snapshot by classifier code, lists supported kinds (okpd2, ktru, mnn) with examples, and specifies return fields. Distinguishes itself from sibling tools like search_tenders and search_purchase_objects by focusing on aggregated 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?

Explicitly tells when not to use (for pricing data, directing to search_purchase_objects/search_contract_specs) and describes quotas per account type. Could be more explicit about when to use, but context is clear.

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 indicate readOnlyHint=true, and the description adds valuable behavioral details: price masking on free tiers, quota limits for different account types, and error handling (isError with instructions). This goes beyond 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?

The description is fairly concise and front-loaded with purpose, then adds quota and behavioral info. It could be slightly shorter, but it earns its length with important details.

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 13 parameters and no output schema, the description covers search scope, aggregates, and error scenarios reasonably well. Lacks response format details but is adequate for a search 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?

Despite 100% schema description coverage, the tool description lists some searchable fields (MNN, trade name, etc.) that correspond to parameters but does not add new meaning beyond the schema. Baseline score 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 it searches contract specification lines by various pharmaceutical attributes and returns aggregates. However, it does not explicitly distinguish itself from sibling tools like search_tenders or search_purchase_objects, though the context implies it is for contract specs.

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 context on usage (free tier price masking, quota limits) but lacks guidance on when to use this tool versus alternatives or when not to use it. No explicit comparison to siblings.

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?

The description discloses important behavioral traits beyond annotations: data masking on free tiers (teaser), quota limits for different account types, and error behavior when quotas are exceeded. This provides critical context for an AI agent to manage expectations and fallback actions. Annotations only indicate readOnlyHint=true, so the description adds significant value.

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 coherent paragraph but is slightly verbose, including detailed quota information. However, it is well-structured: first the core functionality and output, then use case, then limitations and quotas. All sentences are relevant and earn their 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?

Given the tool's complexity (11 parameters, no output schema), the description is remarkably complete. It explains the output structure (lines with fields and parent data), the intended use case, data limitations (teaser), quota restrictions, and error response on quota exceed. This fully compensates for the lack of output schema and provides an agent with all necessary 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?

Schema coverage is 100%, so baseline is 3. The description does not add additional meaning to parameters beyond what the schema provides; it focuses on output structure and limitations. No extra context is needed for parameters as they are fully described 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?

The description clearly states that the tool searches purchase object items (товарные позиции извещений), explains the data structure (each line is a purchase object with name, OKPD2, quantity, price, sum) and parent notice data. It distinguishes from sibling tools by specifying it is product-level, not whole purchase, and gives a concrete use case: 'who buys a specific product and at what price'.

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 explicitly states when to use the tool: for questions about specific product purchasing. It implies not for whole-tender queries. It does not name sibling tools as alternatives, but the context signals list them separately, and the description provides clear context by saying 'this is the product level, not the whole purchase'.

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?

Despite annotations marking readOnlyHint, the description adds behavioral details: returns list structure, period and includeTotal effects, quota limits, and error indication. No contradiction with 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?

Description is a single paragraph covering all essential aspects. It is informative but slightly dense; could be more scannable with bullet points, but still effective.

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 no output schema, the description compensates by enumerating returned fields. It covers all 10 parameters, quotas, error handling, and performance. Sufficient for an agent to use 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?

All 10 parameters have schema descriptions (100% coverage). The tool description enriches understanding by explaining defaults, performance implications (e.g., 'all' period is slower), and quota effects, adding value beyond 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?

The description clearly states the tool searches for Russian state procurement notices by text and filters (region, customer, NMCK, period). It distinguishes from sibling tools like get_tender by focusing on search and listing.

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 default for period, performance notes, quotas, and error behavior. However, it does not explicitly state when to use this tool versus alternatives like get_tender or search_contract_specs.

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