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?
With no annotations present, the description carries the full burden and does a good job: it discloses the maximum of 10 candidates, the returned fields (name, legal_name, city, domain), and the fact that legal_name appears only when it differs from the statutory name. It does not mention edge cases like no matches or behavior when no parameters are provided, but the core behavior is transparent.
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 compact, front-loaded with the search purpose, and adds only high-value details: examples, output fields, the slug link, and the sibling alternative. Every sentence earns its place with no 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 lookup tool with low complexity and no output schema, the description gives enough context: search criteria, examples, returned fields, result cap, and an explicit pointer to a sibling for ranked use. It could be slightly more complete by explaining the city and limit parameters, but it is otherwise well-rounded.
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 0% description coverage, so the description must compensate. It explains name and domain with concrete examples, but it does not explain the city parameter or the limit parameter in terms of how they affect the search. The mention of 'max. 10 kandidaten' hints at limit's upper bound but does not clarify that limit is configurable or that city is an optional filter.
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 finds a specific agency by handelsnaam, statutaire naam, or domain, and that it produces the slug needed for get_agency_profile. It also distinguishes itself from search_agencies by positioning itself as the targeted lookup option rather than a ranked recommendation tool.
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 search_agencies for ranked agency advice based on criteria, which makes the boundary between the two tools clear. It also implies the correct workflow: find the agency to obtain the slug, then use get_agency_profile.
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.
find_agency is explicitly an exact-name/domain lookup that returns a slug, while search_agencies is clearly a criteria-based ranked discovery. get_agency_profile and submit_rfq occupy completely distinct roles, and the descriptions cross-reference each other to remove any ambiguity.
All four tools follow a consistent snake_case verb_noun pattern: find_agency, get_agency_profile, search_agencies, submit_rfq. The verb clearly describes the action and the noun clearly identifies the target resource.
Four tools form a tight, purposeful set for the agency discovery and RFQ submission workflow. There is no redundancy, and each tool earns its place in the server's scope.
The core user journey is covered: find an agency, view its profile, search by criteria, and submit an RFQ. Minor gaps are the lack of RFQ status tracking after submission and no pagination beyond the 20 search results, but these are workable within the stated scope.