List entities of one type, optionally filtered. Companies filter by sector/country/q; assets by type (Crypto|Index|Bond|Currency|Commodity). Returns up to limit records (default 25).
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Substring filter across all fields | |
| type | No | ||
| limit | No | ||
| sector | No | ||
| country | No | ||
| entity_type | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden; it discloses the default limit and type-specific filter behavior for companies and assets. However, it does not mention pagination, result shape, or behavior for other entity types, leaving notable gaps.
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 and front-loaded with the core operation, including concrete filter and limit details without redundancy. It is concise, though slightly terse given seven entity types and six parameters.
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?
The description plus schema enables basic calls with entity_type, q, limit, and the company/asset filters, but it leaves the remaining four entity types and their parameter applicability undocumented. The lack of an output schema also means return-value semantics are unstated.
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 only 17%, so the description must add meaning; it does clarify q, limit, sector/country for companies, and the type enum for assets. Other params and entity types such as funds, banks, and markets remain unaddressed, and 'type' is only explained in the asset context.
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 names a clear operation — 'List entities of one type' — and specifies filterable fields for companies and assets. It does not explicitly distinguish itself from sibling tools like search or lookup, but the entity-type scoping makes the purpose reasonably distinct.
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?
No guidance is given on when to use list versus alternatives such as search, lookup, or graph. It explains filtering mechanics but not selection criteria, exclusions, or when another tool would be preferable.
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 distinct retrieval mode: search/list for discovery, lookup/resolve_identifier for exact entity access, graph for relationships, live_data for reference values, and ingest_text for text extraction. Despite several retrieval tools, their input/output contracts are clearly separated in the descriptions.
Names are mostly lowercase and readable, but they mix single-word commands (graph, list, lookup, search), noun phrases (live_data), and verb_noun compounds (ingest_text, resolve_identifier). There is no consistent verb_noun pattern, so the set feels slightly ad hoc.
Seven tools cover the server's read-only knowledge-base scope without bloat: each operation (discover, resolve, look up, traverse, get live data, ingest text) maps to exactly one tool. This is well within the ideal 3–15 range.
The surface covers the main entity lifecycle: search/list to find, lookup/resolve_identifier to retrieve, graph to expand relationships, live_data for current values, and ingest_text for parsing text. Minor gaps such as schema introspection or historical time-series would require workarounds, but core workflows have no dead ends.