gp_exitsList the exits (realised divestments) of a private equity firm, optionally for a specific year. The query AI search cannot answer reliably: 'what did GP X sell in YEAR'. Returns company, exit year, exit route, hold period.
| Name | Required | Description | Default |
|---|---|---|---|
| gp | Yes | PE firm name | |
| year | No | Exit year filter, e.g. 2024 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds return fields (company, exit year, exit route, hold period) and reliability hint. Annotations already declare readOnlyHint=true, so no contradiction.
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, efficient: purpose, optional parameter, usage hint, return fields. No wasted words.
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?
Covers purpose, usage scenario, and return values. Lacks mention of pagination or error handling but sufficient for a simple list tool with good annotations.
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 already covers both parameters with descriptions (100% coverage). Description adds only context of optionality, not new semantic meaning beyond schema.
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?
Clearly states verb 'list', resource 'exits', and context 'PE firm' with optional year. Distinguished from siblings like 'search_exits' by focusing on a specific GP.
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?
Explicitly notes when to use (when AI search cannot answer reliably for GP and year). Could be more explicit about alternatives (e.g., use search_exits for cross-firm queries).
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 unique purpose: gp_exits and gp_portfolio are per-firm, while search_exits and search_deals are cross-firm, clearly differentiated by scope. search_companies, search_gps, and who_owns cover distinct entity types and actions, leaving no ambiguity.
Tool names use a consistent verb_noun pattern for search_* tools and a gp_* prefix for per-firm tools, but who_owns breaks the convention with a question phrase. The inconsistency is noticeable but does not severely impair usability.
With 7 tools, the server is well-scoped for its domain, covering per-firm and cross-firm queries, entity searches, and ownership history without redundancy or bloat.
The toolset covers the core private equity data needs: searching firms and companies, viewing portfolios and exits for a specific GP, cross-firm deal and exit searches, and ownership lookup. Minor gaps like detailed company financials are outside the apparent scope.