search_closelookSearch Closelook’s research corpus: 101 explainers, glossary, heresies (contrarian theses), reports, strategy notes and the finance library. Returns matching pieces with a one-line summary and link. Use for "what has Closelook written about X".
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Restrict to one content type (default all) | |
| query | Yes | Keywords, e.g. "memory supercycle" or "sector rotation" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and non-destructive; description adds the specific return format (one-line summary and link) and scope of the corpus, providing useful behavioral context beyond annotations.
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?
Single sentence with clear structure, listing content types and usage guidance without redundancy.
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 search tool with two parameters and no output schema, the description covers purpose, return format, and scope, making it adequately complete.
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 parameters are fully documented in the schema. The description adds the use case but no additional parameter semantics beyond what schema provides.
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 searches Closelook's research corpus, enumerates content types, and mentions returns with summary and link, distinguishing it from sibling tools like define_term.
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 states 'Use for "what has Closelook written about X"' providing clear usage context, but does not explicitly mention when not to use it or alternatives.
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.
Most tools map cleanly to a distinct Closelook surface — indices, macro boards, rankings, research, tape, wires. There are a few near-neighbor pairs like get_df_ranking vs get_ranking and get_market_instrument vs get_stock_snapshot, but the detailed descriptions resolve most potential misselection.
Every tool follows a clear imperative verb + noun pattern — get_, define_term, compare_indices, search_closelook — with consistent snake_case and essentially all resource-oriented nouns. The naming is predictable and easy to navigate.
25 tools is on the heavy side, above the typical well-scoped range, but each endpoint maps to a meaningful product area of Closelook's public site. The count is justified by the breadth of a financial intelligence service, though it could have been trimmed slightly.
The tool surface covers the major Closelook workflows: indices, rankings, macro monitors, stock-level data, earnings, wires, research search, and portfolio snapshots. For a read-only intelligence server there are no obvious dead ends — depth and background material is paired with lookups and daily updates.