Find companies by name (case-insensitive substring). Returns id, location and verified funding totals; pass the id to get_company for the full profile.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Company name or fragment, e.g. "Theker", "mistral" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, covering safety and non-exhaustive results. The description adds useful behavioral details: case-insensitive substring matching and the returned fields (id, location, verified funding totals). It does not elaborate on open-world aspects like result limits or pagination, but annotations cover that baseline.
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, front-loaded with the primary action, and every phrase adds value: matching mode, returned fields, and a pointer to get_company. 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 one-parameter search tool with strong annotations and no output schema, the description is complete. It covers the search semantics, return content, and onward workflow. The openWorldHint annotation handles potential result size ambiguity, so no further detail is necessary.
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 a documented 'query' parameter, so the baseline is 3. The description adds the case-insensitive substring behavior, which the schema does not explicitly state. This extra semantic nuance helps the agent understand how to form queries and what results to expect.
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 begins with 'Find companies by name (case-insensitive substring)', which is a specific verb, resource, and matching semantics. It clearly differentiates from siblings like get_company (which retrieves by id) and other search tools (search_investors, search_rounds) by focusing on company name lookup.
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 instructs to 'pass the id to get_company for the full profile', providing a clear next step and implicitly distinguishing this tool as a lightweight search. It does not explicitly mention when not to use it relative to other search tools, but the name and sibling context make the appropriate use case evident.
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 has a clearly distinct purpose: company search, full profile, investor profile, aggregate market map, and searches for exits, investors, and rounds. No overlap or ambiguity.
Tools follow a verb_noun pattern consistently (find_companies, get_company, search_exits, etc.). 'market_map' is also verb_noun but slightly less conventional, making it a minor deviation.
Seven tools is well-scoped for a European funding explorer, covering essential operations without being excessive or insufficient.
The set covers company and investor details, funding rounds, exits, and aggregate data. Minor gaps exist (e.g., limited filtering on search_rounds), but core functionality is solid.
