Search Agent Papers companies by name or tagline, optionally constrained by category and status. Returns compact vendor records for ranking.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Substring to match against company name and tagline. | |
| status | No | Optional company or offering status filter. | |
| category | No | Optional category filter. |
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 that it matches name/tagline, supports filters, and returns 'compact vendor records for ranking,' which is useful behavioral information. However, it omits details like pagination, result limits, ordering, or what happens when no match is found, leaving some behavioral 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?
Two sentences, each earning its place. The first states the action and scope, the second describes the output. No redundant or filler content.
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?
With no output schema, the description should explain return values more thoroughly. It says 'compact vendor records for ranking' but does not specify the record structure or whether multiple results are returned. The input parameters are well covered, but the output side is vague, leaving the description incomplete for a fully self-sufficient 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?
Schema description coverage is 100%, so the baseline is 3. The description adds minor context by explicitly tying the query to name/tagline and the optionality of category and status, but these are largely already in the schema descriptions. No significant new parameter semantics are introduced.
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 identifies the resource ('Agent Papers companies') plus the searchable fields ('by name or tagline'). It clearly distinguishes from sibling tools like get_company by focusing on search-based discovery rather than exact retrieval.
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 gives clear context: use this when looking up companies by name/tagline, with optional category and status filters. It does not explicitly mention alternatives or exclusions, but the scope is unambiguous and appropriately set within the sibling tool suite.
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 resource and action: search for discovery, get_company for full details, compare for category matrices, list_categories for browsing, get_schema for metadata, and whats_new for changelog. There is no meaningful overlap between any tools.
Most tools follow a verb_noun pattern (get_company, get_schema, list_categories), but 'compare' and 'search' are bare verbs, and 'whats_new' is a noun phrase rather than a verb. The mixture of styles is noticeable but still readable.
With 6 tools, the server is well-scoped for a read-only registry exploration. Each tool earns its place, and the count is neither too thin nor overly heavy for the apparent purpose.
The surface covers the full exploration lifecycle: listing categories, searching, fetching details, comparing, understanding schema, and tracking updates. For a read-only registry, there are no obvious missing operations that would hinder an agent.
