Bulk fetch records from a CZ ARES sub-register

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

The description adds significant behavioral context beyond annotations. It states the tool uses POST /ekonomicke-subjekty-{source}/vyhledat upstream, which is an important implementation detail. It also mentions pricing: 'Pricing: free' and error response: 'Other jurisdictions return 501'. The output format is described: 'Returns `{ source, pocet_celkem, count, records[] }`' with caveat about variable fields. Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, which are consistent and reinforced.

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 clear sections (CZ source codes, usage notes, return info, pricing). It is front-loaded with a clear one-sentence purpose statement. However, it could be slightly more concise; the extensive list of source codes could be summarized with a reference to get_specialised_record's list, but the duplication provides convenience. Minor redundancy in mentioning the upstream endpoint twice.

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 moderate complexity (6 parameters, 1 enum, output schema present), the description is complete. It explains the return format, refers to external documentation for field details, and covers edge cases (e.g., missing ico yields all records, other jurisdictions error). The output schema exists (as indicated by context signals), so return value explanation is sufficient. No gaps remain.

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 has 100% description coverage, providing clear descriptions for each parameter. The tool description adds value by: (1) listing all source codes with descriptions, (2) explaining the IČO auto-padding behavior ('auto-padded'), (3) providing context about the 'ico' parameter: 'If omitted, ARES returns the first page of all records in the register (rarely useful — prefer a filter).' This is helpful guidance beyond the schema.

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

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

The description clearly states the tool's purpose: 'Fetch raw records from one specific ARES source register in a single call'. It specifies the verb (fetch), resource (records from ARES sub-register), and scope (bulk, specific source, optionally filtered by IČO). It also differentiates from its sibling get_specialised_record by noting it is the 'paired search endpoint for get_specialised_record (which fetches one record at a time)'. This distinction is further emphasized by referencing the upstream POST endpoint.

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 explicit guidance on when to use this tool: for bulk fetching from a specific ARES source. It clearly states when not to use it: 'For rich name/address/legal-form search, use search_companies'. It also mentions limitations: 'The upstream filter is intentionally narrow — ARES only accepts an optional list of IČOs plus pagination on these per-source endpoints.' This helps the agent avoid misuse.

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