earnings_calendarUpcoming and recent earnings dates with EPS and revenue estimates. Pass symbol for one company; omit it for the market-wide calendar. FMP serves this endpoint market-wide only, so a symbol is filtered on our side and the response says how wide a window was searched.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ||
| from | No | ||
| symbol | No | Ticker to filter to, e.g. "CRM". Omit for the whole market. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context about the FMP backend limitation (market-wide only) and the local filtering behavior, plus that the response includes the searched window. This goes beyond the annotations without contradicting them.
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?
Three concise sentences: the first states purpose, the second explains usage, the third adds a behavioral nuance. Every sentence earns its place with no waste.
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 covers the core functionality and even notes the response includes window search information. However, it omits explanation of the from/to date parameters and the overall output structure, leaving gaps for an agent to fully understand the tool's interface.
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?
Only the symbol parameter has a schema description, and the description clarifies its optionality. However, the from and to parameters are not explained in the description, leaving their format and semantics ambiguous. With schema coverage at only 33%, the description should compensate but does not.
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 provides 'upcoming and recent earnings dates with EPS and revenue estimates', and explains the two modes of use (with or without symbol). This differentiates it from sibling calendar tools like economic_calendar or ipos_calendar.
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?
It explicitly instructs to pass a symbol for one company or omit it for the market-wide calendar, giving clear usage context. However, it does not mention alternatives or when not to use this tool.
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.
Multiple tools overlap in purpose: quote/quote_short/historical_price/intraday for price data; balance_sheet/income_statement/cash_flow for financials; search_symbol/search_name/discover_tools for lookup; and a cluster of Pipeworx routers (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, validate_claim) with unclear boundaries. Agents will frequently select the wrong tool.
All tool names use consistent snake_case, but naming conventions vary widely: noun phrases (balance_sheet, entity_profile), bare verbs (forget, subscribe), verb+noun (compare_entities, resolve_entity), and adjective+noun (historical_price, recent_alerts). No single pattern dominates, making it harder to guess tool names.
55 tools is excessive for a server labeled 'Fmp'. The core financial data tools are perhaps 20-25, while the rest are unrelated: memory utilities, prediction market analyzers, web scraping, and meta-routing tools. This bloated set dilutes the server's purpose and burdens the agent with irrelevant options.
For the declared domain (FMP financials), the set covers the main statements but lacks tools like segment data, insider trades (listed as paid), or ownership details (also paid). Conversely, it includes many tools for prediction markets and general data retrieval that don't belong here, creating a mismatch between server name and actual capability.