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

With no annotations provided, the description carries the burden of disclosing behavior. It states the tool returns ESG scores, classifications, and metadata, which implies a read-only comparison. However, it does not disclose potential error behavior, sorting order, or any other side effects, leaving some ambiguity.

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, front-loaded sentence that immediately conveys the core functionality and output. Every word adds value, with no filler or 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 low complexity (one array parameter) and the lack of an output schema, the description adequately covers the essential return values ('ESG scores, classifications, and metadata for each company'). It could be slightly more explicit about output formatting, but it is sufficiently complete for a comparison 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?

The schema already provides 100% coverage for the single parameter 'companyIds' with a clear description ('Array of 2-5 company pro IDs to compare'). The tool description adds no additional parameter-level meaning beyond what the schema documents, so the 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 action ('Compare'), the resource ('2-5 companies'), and the comparison mode ('side by side'). It also outlines the returned content (ESG scores, classifications, metadata), which distinguishes it from single-company tools like get_company_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?

The phrase 'Compare 2-5 companies side by side' gives clear context for when to use the tool and implies it is for multi-entity comparison rather than single-company lookup. However, it does not explicitly mention when not to use it or name alternative sibling tools.

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 only states that it gets a ranking, but does not disclose how ranking is computed, what data is returned (e.g., scores, company names), or any edge-case behavior. This is minimal 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?

Two concise sentences fully convey the core action and the optional filter. No redundant words; the structure front-loads the main purpose.

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?

Without an output schema, the description should clarify what the ranking looks like (e.g., sorted list with scores, whether it includes the company itself). It does not, leaving a significant gap for an agent to know what to expect from the response.

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 includes detailed descriptions for both parameters. The description's mention of an optional ESG category adds no new meaning beyond the schema, which already explains the category enum and the default average ranking. Baseline 3 applies.

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

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

The description clearly states the verb ('Get'), the resource ('ranking of all companies within the same activity'), and the optional filter ('by ESG category'). This distinguishes it from sibling tools like list_companies_by_activity, which list companies without ranking.

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 the tool: when you need a ranked list of companies sharing an activity with a specified company. It provides clear context (companyId identifies the activity) and an optional category filter, though it does not explicitly name alternatives 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 provided, the description carries the full burden of behavioral disclosure. It mentions the return shape ('criterion names, coefficients, and scores') but does not explicitly address read-only behavior, error handling, or authentication requirements. For a get operation, this is moderate 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 two concise sentences with no redundant information. It front-loads the verb and resource, and the second sentence adds valuable return details without 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?

This is a simple tool with only two parameters and no output schema. The description covers both the input scope (company and ESG category) and the expected output, making it complete enough for an agent to invoke 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 input schema provides full coverage for both parameters, including descriptions and an enum for the category. The description does not add parameter-level meaning beyond what the schema already offers, so the baseline 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 verb 'Get' and the specific resource: 'detailed evaluation criteria for a company in a specific ESG category.' It also lists what is returned, distinguishing it from sibling tools like get_company_profile and get_activity_ranking.

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 when evaluation criteria are needed, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. No comparison with sibling tools is given.

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 discloses the data fields returned, which is useful. However, it does not mention any required permissions, whether the operation is purely read-only, or any potential side effects. For a simple get tool, this 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 a single, well-structured sentence that names the resource and lists its key contents. No filler or repeated schema information. Every word 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?

For a tool with only 1 parameter and no output schema, the description adequately enumerates the expected response contents (E/S/G scores, classifications, sector, activity, verification date). It does not specify formatting or pagination, but none is needed for a single-profile get. Minor gap: no mention of error conditions, but 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 coverage is 100% (companyId is fully described with type, description, and constraint). The description does not add extra parameter meaning, but the schema already provides sufficient semantics, including the clue that the ID comes from search or listing. This meets the baseline of 3.

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 states a specific verb ('Get') and resource ('company's ESG profile'), and enumerates the contained data (E/S/G scores, classifications, sector, activity, verification date). This clearly distinguishes it from siblings like get_company_criteria or compare_companies, which target other 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 implies usage (when you have a company ID and need its ESG profile) but does not explicitly state when to use it versus alternatives like search_company or get_company_criteria. The parameter description adds context ('from search or listing') but the tool description itself offers no direct comparison or exclusion.

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 required input (sector slug) but does not mention any behavioral traits such as pagination, filtering, error handling, or what is returned (e.g., IDs vs. names). This is minimal disclosure for a tool without annotation support.

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, front-loaded with the core action and immediately followed by the prerequisite. There is no wasted wording or irrelevant 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?

Considering the tool's simplicity (one parameter, no output schema, no annotations), the description adequately covers purpose and prerequisite. However, it leaves the return format unspecified, which could be a minor gap for a list-returning tool. Still, the context is complete enough for the low 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?

The single parameter sectorSlug is fully described in the schema with 'Slug of the sector (from list_sectors)', and the description repeats this dependency. Since schema coverage is 100%, the description adds no major new meaning, just reinforces the source of the 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?

The description clearly states the tool's purpose: listing activities (sub-categories) within a given sector. It distinguishes itself from sibling tools like list_sectors (which lists sectors) and list_companies_by_activity (which lists companies by activity).

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 mentions the prerequisite of needing a sector slug from list_sectors, providing clear context on when this tool should be used (i.e., after obtaining a sector slug). It does not explicitly exclude alternatives, but the dependency is clearly stated.

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 pagination support, return fields, and the noteworthy behavior of including unscored companies. This goes beyond the schema but does not specify the exact ranking order or pagination response structure, which would be further valuable.

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, front-loaded with the primary action and followed by relevant details (pagination, return fields, unscored companies). Every sentence contributes meaning, with 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?

For a simple list tool with 2 parameters and no output schema, the description covers key aspects: the scope (specific activity), pagination, and what is returned, including unscored companies. It is sufficiently complete but omits details like resulting order or response format, which are not captured elsewhere.

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 already provides descriptions for both parameters (activitySlug and page) with a cross-reference to list_activities. The tool description adds little beyond the schema, only restating the activity slug source, so the baseline of 3 applies.

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

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

The description clearly states the tool lists companies ranked within a specific activity, includes pagination, and specifies return fields (names and IDs). It distinguishes from siblings like list_activities and get_activity_ranking by emphasizing activity-specific scoping and inclusion of unscored companies.

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 for when to use the tool (to list companies by activity) and references list_activities for obtaining the slug. However, it does not explicitly contrast with similar siblings like get_activity_ranking, which might offer a ranked view, so lacks explicit exclusions or 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?

With no annotations, the description carries the burden but only discloses that it returns sector names and slugs. This is useful but does not cover potential pagination, ordering, or any read-only guarantee. For a simple list operation, the disclosure 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 short sentences, front-loaded with the action and resource. Every word adds value, with no redundancy or filler.

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

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

Given the simplicity of the tool (no parameters, no output schema), the description is nearly complete. It states the output format (names and slugs), which is the main contextual need. A minor addition could be explicit mention of use cases, but it is not essential.

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, so the baseline is 4. The description correctly implies no parameters are needed, and the schema is trivially complete. No additional parameter semantics are required.

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 action ('List') and the resource ('all ESG/CSR sectors available on Zei World'), and specifies the return value ('sector names and slugs'). This distinguishes it from sibling tools like list_activities, which targets a different entity type.

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. It does not mention that list_activities should be used for activities or that list_companies_by_activity is for companies. The description only states what it does, leaving the selection entirely to the agent's inference.

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 transparently states the behavior ('Returns matching companies with their IDs') and the scope ('across all brands'), but does not disclose potential partial matching, sorting, or error behavior. This 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 a single, clearly worded sentence with no wasted words. It efficiently states the action, scope, and return 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?

For a simple search tool with one parameter and no output schema, the description is sufficiently complete. It covers the search target, scope, and output format. It could mention that it returns a list, but 'matching companies' implies this. No significant gaps given the tool's simplicity.

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 only parameter (query) is fully described in the schema ('Search query (company name)') and matches the description's 'by name'. With 100% schema coverage, the description adds little beyond the schema, only clarifying the cross-brand scope, so 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 uses a specific verb ('Search') and resource ('company by name across all brands'), and clearly states the return value (matching companies with IDs). It distinguishes itself from sibling tools like list_sectors or get_company_profile by focusing on name-based search.

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 you need to find a company by name and retrieve its ID, but it does not explicitly contrast with alternatives or state when not to use it. The context of sibling tools makes the purpose clear, but there is no direct comparison.

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