All currently valid, evidence-backed facts for one entity — each with source, filing reference (e.g. SEC accession number), period, retrieval time, license and a citable fact_url. Optionally filtered to one predicate such as 'revenue' or 'total_assets'. Use for 'what do we know about X' and for exact reported values with verifiable provenance.
| Name | Required | Description | Default |
|---|---|---|---|
| entity | Yes | ||
| predicate | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and idempotent behavior. The description adds valuable behavioral context: facts are 'currently valid' and 'evidence-backed', and the return payload includes source, filing reference, period, retrieval time, license, and fact_url. 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?
Two dense sentences carry both the return-value contract and usage guidance with no filler or redundancy. The core scope ('All currently valid... facts for one entity') is front-loaded, and every clause adds useful information.
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?
Given no output schema, the description compensates by enumerating the key fields returned (source, filing reference, period, retrieval time, license, fact_url) and explains the optional predicate filter. It is complete enough for an agent to understand what the tool returns and when to call it, though it could slightly clarify how entity identifiers are specified.
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?
With 0% schema description coverage, the description must compensate. It explains 'entity' as the target of fact retrieval and 'predicate' as an optional filter with concrete examples ('revenue', 'total_assets'). While entity identifier format is left implicit, the param semantics are substantially clarified.
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 identifies a specific retrieve operation for all currently valid facts about one entity, clearly distinguishing it from a search-oriented tool. It names the entity scope and optional predicate filter, and gives concrete use cases ('what do we know about X', 'exact reported values'). The resource and action are unambiguous.
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 prescribes when to use this tool: for entity-level fact gathering and for verifiable reported values. It does not explicitly state when not to use it or name alternatives like search_facts, but the stated use cases give clear contextual guidance.
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.
get_facts, query_template, and search_facts all return fact-like results and can overlap when an agent needs a specific reported value; the descriptions attempt to differentiate curated vs. full-text paths, but the boundary is not crisp. lookup_entity, list_templates, and mcp_server_history are clearly distinct.
Most tools follow a verb_noun pattern: get_facts, list_templates, lookup_entity, query_template, search_facts. mcp_server_history breaks the pattern by using a bare noun phrase, which is inconsistent with the rest of the set.
Six tools is a well-scoped size for a fact-registry MCP server. The count is neither bloated nor too thin, though mcp_server_history feels somewhat unrelated to the core fact-querying purpose.
The server covers the main read-side needs of the domain: entity resolution, full-text search, direct fact retrieval, and template-based structured queries. Minor gaps exist, such as no tool to fetch a single fact by fact_url or inspect historical changes to a fact, but core workflows are supported.