Skip to main content
Glama

Openfema

by io.github.pipeworx-io

Disaster Declarations

disaster_declarations
Read-onlyIdempotent

Look up and COUNT US federal disaster declarations (FEMA DisasterDeclarationsSummaries). Filters: state (2-letter), incidentType (e.g. 'Fire', 'Flood', 'Hurricane', 'Severe Storm'), declarationType ('DR' major disaster, 'EM' emergency, 'FM' fire management), year (fyDeclared, the federal FISCAL year), and since/until for a real calendar date range — use since/until for questions like 'in the past year', which a fiscal year does not answer. Counts are DISTINCT DISASTERS by default, not table rows: FEMA publishes one row per disaster per designated county, so Hurricane Harvey is ~60 rows for Texas but one declaration. Pass designatedArea or grain:'area' for county-level rows. Returns the most recent first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoFederal FISCAL year declared (fyDeclared), e.g. 2024. For a calendar window use since/until instead.
grainNo'disaster' (default) = one record per declaration; 'area' = one record per designated county.
limitNoMax records (default 50, max 1000).
sinceNoOnly declarations on/after this date — ISO 'YYYY-MM-DD'. Use with until for windows like 'the past year'.
stateNo2-letter state/territory code, e.g. 'CA', 'TX'.
untilNoOnly declarations on/before this date — ISO 'YYYY-MM-DD'.
orderbyNoOData $orderby, default 'declarationDate desc'. Live-API path only.
incidentTypeNoIncident type, e.g. 'Fire', 'Flood', 'Hurricane', 'Severe Storm'.
designatedAreaNoFilter to a designated area, e.g. 'Harris (County)'. Implies county-level grain.
declarationTypeNo'DR' (major disaster), 'EM' (emergency), or 'FM' (fire management).

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the read-only annotations, the description discloses crucial behavioral nuances: counts are DISTINCT DISASTERS by default, not table rows, and explains why (one row per county), including the Hurricane Harvey example. Also states the default ordering ('most recent first'), preventing misinterpretation of results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence in the description carries valuable information: purpose, filter list, count behavior, date-range guidance, and ordering. Despite being dense, it avoids redundancy and is well-structured, front-loading the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's key behaviors and edge cases thoroughly, especially the count semantics and granularity controls. With no output schema, it could enumerate return fields, but the current detail is sufficient for selecting and invoking the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already has 100% coverage, but the description adds meaningful context by explaining the fiscal-year vs calendar-date distinction and how grain/designatedArea affect the output granularity. This goes beyond the schema's property descriptions, which are already detailed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it 'Look up and COUNT US federal disaster declarations' and names the specific source (FEMA DisasterDeclarationsSummaries). This verb+resource combination distinguishes it from sibling tools, none of which target disaster declarations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use since/until vs fiscal year, and explains the difference between disaster-level and area-level queries via designatedArea/grain. It does not explicitly name alternative tools, but gives clear contextual advice for common query patterns.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Openfema toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

Several tools are near-duplicates or heavily overlapping: ask_pipeworx_beta explicitly matches ask_pipeworx exactly, and ask_pipeworx_grounded, deep_research, and validate_claim all cover grounded-answer territory. The prediction-market cluster (polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, polymarket_edge_tracker, polymarket_kalshi_spread, bet_research) also has fuzzy boundaries that would require careful reading to differentiate.

Naming Consistency2/5

Naming mixes several conventions: verb_noun (query_dataset, resolve_entity, validate_claim), noun phrases (entity_profile, disaster_declarations, deep_research), and branded prefixes (pipeworx_trending, pipeworx_feedback, polymarket_edges, polymarket_arbitrage). Some tools use scan_, some ask_, some list_, with no single predictable pattern across the set.

Tool Count2/5

At 34 tools, the set exceeds the 25+ 'too many' threshold and carries a lot of surface area. The server is named Openfema, yet only about three tools actually relate to FEMA data, making the count feel inflated relative to the stated name and purpose.

Completeness4/5

For its actual broad domain—a general structured-data research gateway—the surface is quite comprehensive: discovery, single lookups, grounded verification, deep multi-source research, entity resolution, comparisons, change feeds, memory, subscriptions, and prediction-market analysis are all covered. Minor gaps exist (e.g., no direct OpenFEMA dataset metadata beyond list_datasets, and some tools require accounts/paywalls), but agents can generally accomplish the intended workflows.

Resources