get_key_figuresThe headline figures for a company's most recent reported period: revenue, net income, diluted EPS and similar, each with its year-over-year change, the exact dollar amount, and the SEC accession number it came from. Start here for any 'how much did X earn' question. Far smaller than get_financials.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes | Ticker symbol, case-insensitive. Examples: NVDA, brk-b. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint. The description adds behavioral context: the tool returns only the most recent period, includes year-over-year change and exact dollar amounts, and cites the SEC accession number. It also warns about response size relative to get_financials. This exceeds the annotation 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?
Two sentences, no fluff. The first sentence fully specifies what is returned; the second provides usage guidance and a comparison. Information is front-loaded and each sentence earns its place.
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 tool with no output schema and strong annotations, the description is complete. It explains the scope ('most recent reported period'), the output fields, and the relationship to siblings. No critical gaps remain.
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% for the ticker parameter, which is well-documented with case-insensitivity and examples. The description doesn't add parameter-level detail beyond the schema, but it indirectly reinforces that the tool operates on a company. Since coverage is high, baseline 3 is appropriate.
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 returns headline figures (revenue, net income, diluted EPS) for a company's most recent reported period. It distinguishes itself from the sibling get_financials by explicitly saying it's 'far smaller' and by anchoring to 'how much did X earn' questions.
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 directs the user to 'Start here' for earnings questions, implying this is the first tool to use. It also contrasts with get_financials by noting size difference. However, it does not explicitly cover when not to use other siblings like get_events or get_narrative, but those are contextually distinct.
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 distinct concern: company identity, event digests, full financials, headline figures, narrative text, and company enumeration. Even the potentially overlapping get_financials and get_key_figures are explicitly differentiated by scope and purpose.
All tool names follow a consistent snake_case verb_noun pattern: get_company, get_events, get_financials, get_key_figures, get_narrative, list_companies. The single list_ verb is still predictable and consistent with the get_ verbs for enumerating a collection.
Six tools is a well-scoped size for a SEC-filing and company-data server. Each tool covers a meaningful slice of the domain without redundancy or unnecessary surface area.
The tool set covers the full read-only workflow: discover coverage, get company identity, retrieve summary or detailed financials, access qualitative narrative, and review recent material events. No obvious dead ends remain for fundamental SEC-based research.