Zoek een specifiek bureau op handelsnaam, statutaire naam of domein (bijv. name='Yourcrew' of domain='yourcrew.online') en krijg de slug voor get_agency_profile. Geeft max. 10 kandidaten met publieke handelsnaam (name), legal_name als de statutaire naam afwijkt, city en domain. Voor gerankt bureau-advies op criteria gebruik je search_agencies.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| name | No | ||
| limit | No | ||
| domain | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of disclosing behavior. It reveals that a maximum of 10 candidates are returned and lists the included attributes (name, legal_name, city, domain). It also signals that results are not ranked by criteria, which is a useful behavioral trait.
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 long and front-loads the core purpose and examples. Every sentence contributes value: the first defines the lookup behavior, the second states output fields and the alternative tool.
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 absence of an output schema, the description adequately describes the return fields and the limit. It also gives concrete examples and a sibling alternative. However, because parameter semantics for city and limit are incomplete, the description is not fully comprehensive for all possible call variants.
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% and there are 4 parameters, so the description must compensate. It adds meaning for 'name' and 'domain' with examples, and 'max. 10' hints at the limit, but it does not explain the 'city' parameter or the 'limit' parameter directly. This leaves a significant semantic gap.
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 a specific verb ('Zoek') and resource ('bureau'), and specifies the search keys: trade name, statutory name, or domain. It also explains the purpose of the result (getting the slug for get_agency_profile), which clearly differentiates it from search_agencies.
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 when to use this tool: to find a specific agency by name or domain. It also provides a direct alternative, search_agencies, for ranked advice on criteria, making the selection between siblings unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct phase: exact name/domain lookup (find_agency), criteria-based ranked search (search_agencies), profile retrieval (get_agency_profile), and RFQ submission (submit_rfq). The descriptions explicitly differentiate find_agency from search_agencies, removing any ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case: find_agency, get_agency_profile, search_agencies, submit_rfq. The verbs are short, active, and clearly reflect each operation with no mixed conventions.
Four tools is a compact, well-scoped set for the server's purpose: discovering, inspecting, and contacting marketing agencies. Each tool has a clear role and no redundancy exists.
The core journey is covered: find/search agencies, retrieve full profiles via slug, and submit RFQs. Minor gaps remain, such as no status tracking for submitted RFQs and no direct tool for listing valid category values (though exposed as a resource).