MCP Market Russia

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

With no annotations, the description must disclose behaviors. It states what the tool does but does not mention idempotency, side effects, error handling, or output nature. The agent learns nothing about safety or behavior beyond the basic function.

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 relatively concise with two clear paragraphs. Purpose is front-loaded. The arg list is detailed but not overly verbose. No redundant sentences.

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 input parameters well but does not describe the output format or return value. Although an output schema exists, it is not visible, so the agent lacks information on what the calculation result looks like. Error handling or limitations are also omitted.

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 0%, so the description fully compensates. It explains each parameter with examples, defaults, and valid values (including translations for material). This adds complete meaning beyond 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 states the tool calculates estimated construction cost using real market data. The verb 'calculate' is specific, and it distinguishes itself from siblings like 'price_comparison' and 'project_estimator' by focusing on market-based estimation.

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?

No explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites, exclusions, or scenarios favoring other siblings. Usage is implied only through the purpose statement.

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 exist, so the description must compensate. It lists included data but does not disclose any behavioral traits (e.g., rate limits, authentication needs, response size). It adds some context but not comprehensive behavioral disclosure.

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 that covers the main purpose and content. It is concise but could be more structured (e.g., bullet points) for readability.

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 an output schema exists, return values need not be detailed. However, the tool has many siblings, and the description covers key data categories but misses parameter explanation, leaving some gaps for an agent.

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 one parameter 'slug' with no description, and schema coverage is 0%. The description does not explain what 'slug' represents or how to obtain it, failing to add meaning 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 'Get comprehensive company profile with all available data' and lists specific data categories (contacts, projects, pricing, etc.), distinguishing it from simpler tools like 'get_company' and other siblings.

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?

No guidance on when to use this tool versus alternatives like 'get_company' for simpler profiles or 'compare_companies' for comparisons. The description only lists content, not use cases or exclusions.

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 full burden. It describes the output (details, projects, etc.) but does not explicitly state it is read-only, disclose any side effects, or mention authentication or rate limits. The safe read operation is implied but not confirmed.

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 short (two sentences plus a parameter line) and front-loaded with the core purpose. No wasted words. The structure is efficient and easy to scan.

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 has only one parameter and an output schema exists, the description covers the main return categories and intended use. It does not discuss potential errors, pagination, or data limits, but for a straightforward read operation it is reasonably 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 0%, so the description must compensate. It explains that company_slug comes from search results, which is helpful, but does not provide format, examples, or validation details. For a single parameter, this is adequate but not exceptional.

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 full company portfolio including details, projects, prices, reviews, and contacts. It frames itself as a comprehensive dossier for due diligence or hiring, which distinguishes it from sibling tools like get_company that likely return a subset.

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 mentions a use case (due diligence or hiring) but does not explicitly state when to avoid this tool or direct to alternatives like company_deep_profile or get_company. Usage guidance is implied rather than explicit.

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 states what is compared but does not mention whether the tool has side effects (e.g., is it read-only?), authentication requirements, rate limits, or how it handles invalid or extra IDs. This leaves significant gaps for an agent making decisions.

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 short and front-loaded with the core action. The Args section is somewhat redundant with the input schema but provides useful context. It could be slightly more concise by integrating the parameter detail into the first sentence, but it is not verbose.

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 does not need to detail return values. However, the description does not address error cases (e.g., invalid IDs, fewer/more than 3 IDs) or any limitations. For a simple tool with one parameter, the description covers the essential selection decision but lacks some 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?

Schema coverage is 0%, so the description must add meaning beyond the schema. It clearly explains that 'company_ids' is a comma-separated list of UUIDs, expects 2-3 IDs, and provides an example. This adds significant value over the schema's bare 'type: string' declaration.

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: to compare 2-3 construction companies on specific attributes (prices, ratings, number of projects, specialization). This is a specific verb-resource pair that distinguishes it from siblings like 'get_company' (single company) and 'price_comparison' (focus on prices only).

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 stating 'compare 2-3 companies' and specifying the parameter format, but it does not explicitly state when to use this tool over alternatives (e.g., 'get_company' for a single company, or 'price_comparison' for price-only comparisons). There is no mention of 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 must fully convey behavioral traits. It mentions 'AI-powered' but does not disclose potential latency, approximation, or data requirements. Behavioral implications like randomness or non-determinism are absent.

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 two sentences, front-loading the core function. However, it could add more detail without becoming verbose. Every sentence adds value.

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 7 optional parameters with 0% schema coverage, the description fails to sufficiently explain inputs. Output schema exists, so return values are defined, but the tool's complexity is not addressed. The description is too brief for full usability.

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 0%, so description must explain parameters. It mentions 'budget, region, quality requirements' but the schema includes 7 parameters (e.g., need_contacts, need_portfolio) that are unexplained. The mapping to schema fields is incomplete.

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: 'finds the best matching companies based on budget, region, quality requirements' and specifies output as 'ranked list with match scores.' It uses specific verb and resource, differentiating from siblings by highlighting AI-powered matching.

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 does not provide guidance on when to use this tool versus alternatives like 'find_best_companies' or 'smart_match'. It lacks explicit context, exclusions, or scenarios where this tool is preferred.

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 provided, so description carries burden. Discloses return format (CSV text, Excel-ready) and encoding. Does not specify whether it is read-only, authentication requirements, or performance implications. Adequate but could be more comprehensive.

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?

Extremely concise: 6 lines total. Purpose stated first, then parameter list with defaults and ranges. No fluff, every sentence adds value.

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 6 parameters and output schema existing, description covers all input semantics. Return value described as 'CSV text ready to save as .csv'. Could mention that output schema likely defines CSV structure, but description is sufficient for an agent to decide and invoke.

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%, but description explains all 6 parameters: entity options, query, filters (category, region, budget_max), and limit with range. Provides meaningful context beyond schema (e.g., 'budget_max: for companies, cap on min_project_price').

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 'Export search results as CSV text' with specific verb and resource. Including encoding details (UTF-8 with BOM, Excel-friendly) adds precision. Distinguishes from sibling tools like search_companies and search_projects which are for JSON search results.

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 clear context for when to use: exporting search results with filters. Explains parameter semantics (e.g., budget_max for companies). Does not explicitly mention when not to use but implies it is for CSV output, while siblings handle other formats.

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 full burden. It fails to disclose behavioral traits such as read-only nature, authentication requirements, or output format. As a search tool, it should state that it is safe and returns company lists.

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 with a tagline and a bullet list. It is slightly verbose but effectively communicates necessary information. Could be more concise by removing redundant phrases.

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?

Parameters are well-covered, but the description does not mention the output schema or return value. Given the tool has an output schema, the agent lacks context on what data is returned (e.g., company list with fields). This gap reduces 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?

Schema description coverage is 0%, meaning the description provides all parameter meaning. It clearly explains each parameter (region, category, min_rating, etc.) with example values and defaults, adding significant value beyond the input 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?

Description starts with 'Smart lead generation: find the best construction companies matching your criteria.' It clearly states the tool's purpose and differentiates from siblings by mentioning specific use cases like finding contractors and generating leads.

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?

While the description implies usage for lead generation and market research, it does not explicitly differentiate from siblings like 'search_companies' or provide when-not-to-use guidance. The agent must infer context from the tool name and description.

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. It discloses that the tool returns categories with counts but omits any behavioral traits like read-only nature, pagination, or rate limits, which are relevant for a list endpoint.

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 sentence with no wasted words, front-loading the core purpose efficiently.

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 no-parameter tool with an output schema, the description fully explains what it does. No additional context is needed for an agent to select or invoke 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?

The tool has zero parameters, and the input schema coverage is 100%. The description adds no parameter information, but none is needed. The baseline for 0 parameters is 4, reflecting that the description is adequate without further detail.

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 uses a specific verb 'Get' and resource 'company categories' with the outcome 'number of companies in each category,' clearly distinguishing it from sibling tools like 'get_regions' or 'get_stats.'

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 does not provide when-to-use or when-not-to-use guidance, nor does it mention alternatives. However, the tool's purpose is self-evident as a simple listing, and no siblings perform the same function.

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?

Describes a read operation without side effects. No annotations provided, but description does not contradict any. Could disclose more about return format or pagination.

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 concise sentences: first states purpose and included fields, second explains the parameter. No unnecessary 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 one param and an existing output schema (not visible), the description covers what the tool returns. Could be complete enough for this simple 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?

Only one parameter, company_id. Description adds 'Company UUID from search_companies results', providing context beyond the schema type. With 0% schema description coverage, this compensates.

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 'get full company profile' and lists included data (contacts, prices, rating, reviews, house projects). Differentiates from siblings like company_portfolio but may overlap with company_deep_profile.

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?

Implies usage for retrieving full company profile but provides no explicit guidance on when to use versus siblings like company_deep_profile or compare_companies.

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 carry the full burden. It discloses the output format (JSON with status, fields) and that it returns data about a lead. However, it does not explicitly state that the tool is read-only (no side effects) or clarify any behavioral nuances like authentication requirements or potential errors. The disclosure is adequate but not thorough.

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 extremely concise: two sentences totaling about 40 words. It front-loads the purpose, then lists parameters and return value in a structured manner. Every sentence adds value, with no redundancy or fluff.

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 (2 parameters, no nested objects, has output schema), the description provides a clear outline of inputs and outputs. It mentions the return format and fields, which is sufficient for a status-check tool. Slightly higher would require explicit mentions of error handling or pagination, but these are not critical here.

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 0% description coverage, yet the description independently explains both parameters: 'lead_id: UUID returned by request_quote' and 'api_key: the api_key used when the lead was created.' This adds critical context not present in the schema (which only defines types), fully compensating for the lack of 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?

The description clearly states the tool's purpose: 'Check the status of a lead created via request_quote.' It specifies a concrete verb ('check') and resource ('status of a lead'), and distinguishes it from sibling tools like request_quote (which creates leads) and search tools (which find entities).

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 this tool should be used after request_quote to check status, but it does not explicitly state when to use it versus alternatives (e.g., other lookup tools), nor does it explain prerequisites or typical circumstances. The guidance is minimal and could be improved by stating expected use cases or exclusions.

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 burden. It lists the types of information returned (specifications, price, features, company contacts), giving a reasonable idea of the output, but does not explicitly state read-only nature, authentication needs, or error handling. The presence of an output schema slightly compensates.

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 consists of a single informative sentence followed by a concise Args block. Every word adds value, and the key information is front-loaded. There is no redundancy or unnecessary detail.

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 has only one required parameter and an output schema exists (implied by context), the description sufficiently covers purpose, parameter usage, and return content. The low complexity does not require more extensive documentation.

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%, but the description adds an Args section explaining that project_id is a UUID from search_projects results. This provides meaningful context beyond the bare schema that only specifies type string, aiding correct invocation.

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 uses the verb 'Get' and clearly identifies the resource as 'detailed house project information' with specifics like specifications, price, features, and company contacts. It distinguishes itself from sibling tools such as search_projects (summary) and calculation/quote 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 Args section states 'project_id: Project UUID from search_projects results', clearly indicating this tool should be used after search_projects to retrieve full details. While it does not list when not to use it, the context of sibling tools implies its role as a detail retrieval tool.

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 convey behavioral traits. It only states the tool retrieves all regions, without mentioning whether it requires authentication, has rate limits, or any constraints. The output schema exists but the description does not elaborate on behavior beyond the basic 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 a single sentence that efficiently communicates the tool's core function. Every word is necessary and there is 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?

Given the tool's simplicity (no parameters, output schema exists), the description is adequate. However, it could mention if results are sorted, filtered, or if any region hierarchy is applied. Still, it covers the essential purpose 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?

There are no parameters, so schema coverage is 100%. The description adds value by specifying that the output includes the number of companies per region, which is not evident from the empty input schema alone. Baseline for 0 params is 4.

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 all regions and includes the number of companies per region. The verb 'Get' and resource 'regions' are specific, and the tool is well-distinguished from siblings like 'region_comparison'.

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?

No guidance is provided on when to use this tool versus alternatives. Sibling tools exist (e.g., region_comparison, market_analytics) but the description gives no hint about trade-offs 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 is minimal. It implies a read operation but does not disclose any side effects, rate limits, permissions, or data freshness. Adequate for a simple stat tool but not rich.

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 sentence of 12 words, front-loaded with verb and resource, no unnecessary words. Highly concise.

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 stat retrieval tool with no parameters and an output schema present, the description adequately explains what stats are returned. No significant gaps.

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?

Input schema has zero parameters (100% coverage trivially), so baseline is 4. Description adds no param info, but none is needed.

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 verb 'Get' and the resource 'catalog statistics', and lists specific items (total companies, projects, regions, categories, agent queries today, leads generated). This distinguishes it from sibling tools like get_categories or get_regions.

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?

No guidance on when to use this tool versus alternatives. With 23 sibling tools, explicit usage context would help, but it's entirely missing.

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 carry the full burden of behavioral disclosure. The description does not mention whether the tool is read-only, data freshness, rate limits, or any side effects. This is a significant gap for a tool that presumably retrieves data.

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, with a clear statement of purpose, a list of returns, a usage note, and an Args section. It avoids repetition and extraneous detail, though the 'Perfect for...' line could be considered slightly 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?

Given the tool's simplicity (2 optional parameters, no enums, output schema exists), the description covers the core aspects: what it does, what it returns, and how to filter. However, it lacks context on data source, update frequency, or any limitations, which could matter for decision-making.

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 only defines region and category as strings with defaults, no descriptions. The description compensates fully by providing concrete examples ('Москва', 'Строительство домов') and clarifying that empty values mean 'all regions/categories.' This adds substantial meaning beyond the schema, especially given the 0% schema 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 fetches comprehensive market analytics for the Russian construction market and lists specific return values (average prices, top companies, etc.), making the purpose clear. However, it does not explicitly distinguish itself from closely related sibling tools like market_report or trend_analyzer.

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 suggests the tool is 'perfect for investors, analysts, and companies entering the market,' indicating target users. However, it provides no guidance on when to use this tool over alternatives, nor does it mention 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 must disclose behavioral traits. It fails to state whether the tool is read-only, destructive, or its performance characteristics. The listed contents are useful but do not cover behavior.

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 front-loaded, stating the action first, then listing contents, use cases, and parameter in a clear structure. Every sentence adds value with no superfluous 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?

An output schema exists, so return values are covered. However, lacking annotations or mention of whether the tool is read-only leaves a gap. The description is adequate but not 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?

The single required parameter 'region' is described with examples in Russian ('Москва', 'Ленинградская область'), adding meaning beyond the bare schema. With 0% schema coverage, this description compensates well.

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 generates a comprehensive market report for a specific region and lists included contents like market size, price tiers, top players, etc. However, it does not differentiate from similar sibling tools like market_analytics or region_comparison.

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 mentions the tool is 'perfect for investors, business development, and market entry analysis,' giving context on when to use it. However, it lacks explicit when-not-to-use guidance or references to alternative tools among the many 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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It mentions returns of 'detailed price statistics, percentiles, and regional rankings', but does not state whether the operation is read-only, requires authentication, or has side effects. The safety profile is unclear.

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: two sentences plus an Args section. Every sentence adds value, and it is front-loaded with the purpose. No unnecessary 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 the presence of an output schema, return value details are not needed. The tool has few simple parameters and no required ones. The description covers purpose and parameter semantics adequately, but could add behavioral transparency (e.g., read-only hint) to be 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?

The input schema provides only types and defaults with 0% description coverage. The description adds meaning: 'Comma-separated regions' with example and 'Filter by category' with default behavior. This significantly aids agent understanding.

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 function: 'Compare construction prices across regions and categories.' The verb 'compare' and resource 'prices' are specific, and it distinguishes from siblings like 'compare_companies' which compare companies, not prices.

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?

Usage is implied through the argument descriptions (e.g., 'Empty = all'), but there is no explicit guidance on when to use this tool versus alternatives like 'calculate_cost' or 'market_analytics'. No exclusions or prerequisites are mentioned.

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 provided, so description carries full burden. It only says 'estimate' and 'uses real market data' but discloses no behavioral traits like safety, required permissions, or potential side effects.

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 sentence, 20 words, front-loaded with action and key inputs. No redundancy or unnecessary 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?

Covers core functionality with mention of inputs and data source. Lacks specifics on region and category constraints, and with no annotations, safety and behavioral context are absent. Output schema exists but is not described.

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 has 0% description coverage. Description lists all four parameters and specifies quality levels (economy/standard/premium), adding value. However, it does not clarify valid values for region or category, leaving gaps.

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 the tool estimates construction project cost, listing all input factors (area, region, category, quality). It distinguishes itself from siblings like 'calculate_cost' by mentioning real market data, but the primary purpose is 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?

No guidance on when to use this tool versus alternatives like 'calculate_cost' or 'price_comparison'. The description only implies general estimation use without context or exclusions.

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 that the tool shows side-by-side data for multiple regions and lists specific metrics. However, it doesn't explicitly state if the operation is read-only or any permissions/limits. Adequate but not thorough.

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, front-loaded with the main purpose and followed by input format and output content. No unnecessary words or repetition. Highly concise and well-structured.

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 presence of an output schema, return values are handled. The description covers the main parameter and gives a good overview of output columns. However, the missing explanation for 'category' and lack of behavioral details (e.g., read-only) slightly reduce completeness. Still largely 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?

Schema coverage is 0%, so the description adds meaning by explaining the 'regions' parameter as comma-separated region names. However, the 'category' parameter is not mentioned or explained, leaving a gap. For two parameters, partial coverage is mediocre.

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: comparing construction markets across regions, with specific output fields (companies count, ratings, etc.). This distinguishes it from siblings like 'compare_companies' or 'price_comparison', which focus on different aspects.

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 instructs to provide comma-separated region names, implying direct usage for cross-region comparison. While it doesn't explicitly exclude alternatives, the narrow purpose gives good guidance. A brief note on when not to use (e.g., for single region) would improve clarity.

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 full burden. It mentions the return of confirmation with lead ID but lacks details on side effects, authorization, or rate limits.

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 structured with a clear action sentence followed by an Args list. It is reasonably concise, though the Args list could be shortened slightly without losing 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?

While the output schema exists and the description mentions return values, it lacks details on error scenarios and prerequisites. Considering the tool's simplicity, it is adequate but not 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?

With 0% schema description coverage, the description compensates by explaining each parameter's purpose (e.g., 'project_id: Specific project UUID if interested in a particular house project'), adding significant meaning 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 verb 'send' and the resource 'quote request to a construction company', distinguishing it from siblings like 'calculate_cost' and 'get_lead_status'.

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 use when requesting a quote but provides no explicit guidance on when not to use or alternatives like 'compare_companies'.

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 full burden. It describes outputs (sentiment, themes) but does not disclose behavioral traits like idempotency, read-only nature, or potential destructive effects. For an analysis tool, read-only is implied but not stated. Rate limits or authentication needs are also omitted.

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: first defines purpose, second guides parameter usage. Front-loaded with key verb and resource. No wasted words. Could be slightly more structured, but highly efficient for an agent.

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 an output schema present, description need not detail return format. Description covers basic purpose and parameter contexts. However, it lacks details like whether analysis is aggregated or per-review, or if there are limits on data range. For an analysis tool, more completeness about the analysis scope would be beneficial.

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 has 3 parameters with 0% description coverage. Description adds meaning: company_slug for specific company, region/category for market overview. However, it does not specify valid values, formats, or constraints (e.g., region codes, category names). This is minimal additional 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?

Description clearly states it analyzes company reviews, listing sentiment breakdown, common themes, strengths/weaknesses. It specifies the resource (reviews) and the action (analyze), which is distinct from sibling tools like get_company or market_analytics. However, it does not explicitly contrast with siblings, so it falls 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?

Provides guidance on when to use company_slug vs region/category for market overview. This gives clear context for parameter selection. However, it lacks explicit when-not-to-use or mention of alternative tools, e.g., for detailed company info vs. analysis.

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. It discloses the tool returns company details and supports filtering, but lacks details on pagination, authentication needs, or behavior when no results are found. The description is adequate but not rich.

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 paragraphs: a concise one-line purpose statement followed by a structured Args list. Every sentence adds value, with no unnecessary text. It is front-loaded with the key action and scope.

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 has an output schema (not shown), the description need not detail return values. It lists return fields and explains parameters thoroughly. Minor gap: does not mention if search is case-sensitive or supports partial matches, but overall complete enough for a search tool with moderate 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?

With 0% schema description coverage, the description fully compensates by explaining each parameter, including examples (e.g., query: 'каркасные дома недорого'), listing enumerated values for category, and clarifying budget_max behavior ('Set to 0 for no limit'). This adds significant value beyond the schema's type/default.

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: 'Search Russian construction companies by category, region, and budget.' It also lists the returned fields (name, rating, prices, website, phone number), distinguishing it from sibling tools like search_projects or get_company.

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 what filters are available (category, region, budget_max, free text query) and includes examples. However, it does not explicitly mention when to use this tool versus alternatives like find_best_companies or contractor_recommendation.

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, description only states it returns results but doesn't disclose behavior like pagination, rate limits, or whether it's read-only. It's basic but not misleading.

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?

Starts with a clear one-line summary, then lists parameters in a structured docstring. The parameter list is a bit lengthy but necessary due to low schema coverage.

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?

Covers all parameters and return fields (specs, price, link, contacts). Mentions limit maximum 20. Lacks comment on sorting or error conditions, but output schema may fill some gaps.

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 0%, yet description provides detailed explanations for all 8 parameters including units, default behaviors, and accepted values (e.g., material enum). This adds critical meaning beyond raw 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?

States it searches house building projects by specific criteria (area, floors, material, price) and returns specifications, price, link, and contacts. This clearly distinguishes it from sibling tools like search_companies or get_project.

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?

No explicit guidance on when to use versus alternatives (e.g., get_project for a single project, search_companies for companies). The description implies use for general project search but lacks 'when not to use' cues.

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 that the tool returns parsed filters, matches, and an explanation of parsing. However, it does not mention error handling for invalid briefs, rate limits, or authentication requirements, leaving gaps in behavioral 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?

The description is concise with three sentences, each adding value: first sentence states purpose, second gives an example of input, third describes output format. No wasted words, front-loaded for quick understanding.

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 has two parameters, no annotations, and an output schema, the description sufficiently covers input semantics and output structure. It explains the idea behind the brief parameter and the return format, making it complete enough for an AI 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?

The description adds meaning beyond the input schema by explaining that brief is a 'free-form Russian brief' with an example, and top_n is for 'top-N' results. Since schema description coverage is 0%, this is valuable context that clarifies usage.

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: performing a natural-language contractor search using a free-form Russian brief. It specifies the input format and output (parsed filters, matches, explanation), distinguishing it from siblings like search_companies which likely use structured queries.

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 to use it for free-form Russian briefs and mentions that understanding of Russian is required. It implies when to use (when you have a natural-language query) versus structured search tools, but does not explicitly name alternatives or state when not to use. Still, the 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?

No annotations are provided, so the description must disclose behavioral traits. It only says 'Analyze' and 'shows', implying a read-only operation but does not confirm non-destructiveness, auth requirements, rate limits, or what data is returned. The description is insufficient for safe agent planning.

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 concise sentences that front-load the main purpose and add temporal context. No redundant phrasing. Every word 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 tool has parameters, no required fields, and an output schema (not shown). The description does not explain the output format or behavior, e.g., whether results are aggregated, what time granularity is used. For a trend analysis tool, more detail on output and limitations is needed. Annotations are absent, so completeness suffers.

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 mentions three parameters (period, region, category) but provides no details on valid values, meaning, or defaults. 'period' has a default 'all' but no explanation. The description adds minimal value beyond naming the parameters.

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 'Analyze market trends' with specifics like company growth, price dynamics, rating changes, and regional/category scope. It adds temporal context ('developing over time'). However, it does not differentiate from siblings like 'market_analytics' or 'market_report', which could overlap.

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?

No explicit guidance on when to use this tool vs alternatives. The description implies it is for trend analysis over time, but there are no when-not statements or mentions of alternative tools. An agent would need to infer usage from context.

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