Add companies (domain, name, LinkedIn URL, or id) to a watchlist. Returns a per-item result of added, already_present, or unresolved. Free.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Watchlist id. | |
| companies | Yes | Company identifiers: domain, name, LinkedIn URL, or Datahyena id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses meaningful behavior beyond the annotations: it returns a per-item result with states 'added', 'already_present', or 'unresolved', which conveys partial success semantics and idempotency-like behavior. Annotations only provide false hints, so this output detail adds significant value, though auth/permissions or mutation effects are not discussed.
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 concise sentences: the first states the action and accepted inputs, the second explains the return format. Every sentence earns its place with no redundant 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?
Given the tool's moderate complexity (2 required params, no output schema), the description covers the core behavior, accepted input forms, and the return result format. It is sufficient for an agent to select and invoke the tool correctly.
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 schema already documents both parameters thoroughly. The description mostly restates the accepted company identifier types already present in the schema, adding no new parameter-level meaning.
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 ('Add') with a clear resource ('companies... to a watchlist') and enumerates accepted identifier types (domain, name, LinkedIn URL, or id). This distinguishes it from sibling tools like remove_from_watchlist, create_watchlist, get_watchlist, and list_watchlists.
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 implies when to use the tool: when adding companies to an existing watchlist. However, it does not explicitly state when not to use it or mention alternatives such as remove_from_watchlist for removal operations.
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 clearly distinct resource or action: event types (acquisitions, funding_events, exec_moves), entities (companies, investors), and watchlist operations. The watchlist CRUD commands are separated by function, and company_timeline is clearly scoped to a single company's full history.
Watchlist tools consistently use verb_noun (create_watchlist, get_watchlist, add_to_watchlist), while data lookup tools use plural nouns describing the returned entity or event (companies, investors, funding_events). The mixed convention is readable and predictable, with only company_timeline deviating from both patterns.
With 11 tools, the server is well-scoped for its domain: company/event data search plus watchlist management. Each tool has a defined role and the count feels neither sparse nor bloated.
The toolset covers the core domain well: company and investor search, major event types, company timelines, and full watchlist membership management. A notable minor gap is the absence of a delete_watchlist tool, since create/list/get/add/remove exist for watchlists.
