fylings

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

The verb 'fetch' implies a read operation, and the description lists returned fields, which is useful. With no annotations, it does not explicitly state read-only nature, error behavior, or permissions, leaving gaps.

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, well-structured sentence that front-loads the action. The field list adds length but provides valuable output context, making it appropriately 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 read tool with two parameters and no output schema, the description adequately covers invocation and return fields. It lacks explicit error/not-found behavior but is sufficient for basic selection and invocation.

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

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

Schema coverage is 100% with meaningful descriptions for both parameters. The description restates 'by country code and registration number' without adding deeper parameter semantics.

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 'Fetch one company's full record' with specific identifiers (country code and registration number) and lists the returned fields, distinguishing it from siblings like search_companies and get_company_procurement.

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 by requiring country code and registration number, implying use when these identifiers are known. However, it does not explicitly mention when not to use or name 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?

No annotations are provided, so the description carries the burden. It discloses the data source ('open-contracting data') and the returned fields (awarding body, contract title, value, date), which is useful. However, it does not mention pagination, limits on results, or how missing contracts are handled, 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: two sentences that front-load the action and fields, then add a value proposition. Every sentence earns its place 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?

For a simple list tool with two parameters and no output schema, the description provides enough context: it lists the key return fields and data source. However, it could be more complete by noting edge cases like companies with no contracts or geographic coverage, but overall it is sufficient for basic invocation.

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 descriptions for both parameters (country and registration_no) with 100% coverage. The description does not add any additional meaning about the parameters, 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 clearly states the specific verb 'List' and the resource 'government procurement contracts a company has won', with a data source and return fields. This distinguishes it from sibling tools like get_company and search_companies, which focus on company details or search rather than procurement contracts.

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 a clear use case: 'Strong signal of what a company actually does.' However, it does not explicitly state when not to use this tool or mention alternatives by name, though the sibling list implies context. It gives clear context but no exclusions or comparisons.

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 clearly states the tool screens against specific lists and returns matches with a name-match confidence, providing useful behavioral context about data sources and output. It does not mention side effects, authentication, or false-positive caveats, but the core behavior is well disclosed.

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 sentences, begins with the verb 'Screen', and immediately establishes what the tool does and what it returns. There is no redundant or extraneous information, making it 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?

For a simple tool with one parameter and no output schema, the description is sufficiently complete: it explains the purpose, the exact lists queried, and the return value (matches with confidence). It does not delve into fuzzy matching or edge cases, but these are not essential for initial selection and invocation.

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 100% coverage for the single 'name' parameter, so the description does not need to add much. The description repeats the parameter name amd purpose but does not introduce any additional semantic detail beyond the schema, warranting the baseline score 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?

The description uses a specific verb 'Screen' and explicitly names the resources (company/person name) and the three sanctions lists (OFAC SDN, OFAC Consolidated, UN Security Council). This clearly differentiates the tool from sibling tools like get_company and search_companies, which handle company data but not sanctions screening.

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 the tool is for sanctions screening but does not explicitly state when to use it versus alternatives or when not to use it. The siblings are about company information, so the context is somewhat clear, but there is no explicit guidance or mention of 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 must fully disclose behavioral traits. It does this thoroughly: results are ranked by quality, matching is tolerant with detailed match types and scores, empty results contain suggestions, and return fields are listed. This gives the agent a clear picture of what to expect, including edge cases.

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 4 sentences long, front-loaded with the primary purpose and scope. Every sentence earns its place: purpose, matching behavior, return details, and follow-up guidance. No fluff or repetition. It is efficiently structured for quick agent consumption.

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

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

Given no output schema, the description adequately explains the return structure (fields like legal name, registration_no, match_type, etc.) and behavior for empty results. It covers ranking, matching tolerance, and total count. The only minor absence is pagination details, but the limit parameter and total count suffice for basic usage. Overall, it is complete for an agent to understand inputs, outputs, and expected behavior.

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 describes all three parameters with clear descriptions (100% coverage). The description adds behavioral context around the query parameter (tolerant matching) but does not introduce new semantics for the parameters themselves. The limit and country parameters are already well-described in the schema, so the description adds marginal value beyond baseline.

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: searching verified companies across 18 African registries by name or registration number. It is specific about the verb (search), resource (companies), and scope (18 African registries). It distinguishes itself from siblings by noting that for full records one must call get_company, and it is not about procurement or sanctions screening.

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 explains when to use the tool (to search companies by name/registration number) and provides context about result ranking and tolerant matching. It explicitly directs users to get_company for full records, giving an alternative. However, it does not explicitly state when not to use this tool versus the other siblings (e.g., screen_sanctions), though the purpose is sufficiently distinct.

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