fema-mcp-server

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds valuable context beyond those: it clarifies that the row count reflects what was actually staged and instructs checking truncated in the prior response to know if the canvas holds the full set. This is meaningful behavioral disclosure that helps the agent interpret results correctly, going beyond the boolean hints.

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?

Each sentence serves a distinct purpose: what the tool does, when to use it, and an important caveat about row counts. The information is front-loaded and compact, with zero filler. It's an optimal length for quick agent comprehension.

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 discovery tool that feeds a query tool, the description covers the essential context: the source of canvas_id, the need for prior staging via fema_search_nfip, the purpose of discovering schemas, and a pitfall (truncation). Since an output schema exists, the description doesn't need to detail return values. Nothing essential is missing.

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?

The only parameter canvas_id is fully described in the input schema ('Canvas ID from the fema_search_nfip response'), and schema description coverage is 100%. The description does not add extra semantic detail beyond what the schema provides, so the baseline of 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 states the primary action ('List tables and column schemas'), identifies the resource (DataCanvas staged by fema_search_nfip), and explicitly differentiates from the sibling fema_dataframe_query by positioning itself as a prerequisite. This goes beyond a generic 'describe table' and gives the agent an actionable purpose.

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 provides explicit when-to-use guidance: 'Call this before fema_dataframe_query to discover the exact table name, column names, and DuckDB data types needed to write valid SQL.' It also advises checking the 'truncated' field in the fema_search_nfip response, giving the agent a clear decision point. This is strong usage direction that directly influences tool selection order.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true; the description aligns with and reinforces those, adding no contradiction. It contributes beyond the annotations by spelling out exactly which statements are blocked ('DDL, DML, COPY, and file-reading functions'), which is genuinely useful operational context an agent wouldn't otherwise know. The row-cap behavior is mentioned but lives in the schema's query param rather than the description.

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 tight sentences with no filler: purpose, capabilities, prerequisite, and restrictions. The core operation is front-loaded in the first clause, and every remaining sentence earns its place by adding non-obvious information (the describe-first prerequisite and the blocked-statement list).

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 moderate-complexity SQL tool, the description covers purpose, usage context, the mandatory prerequisite, and safety restrictions. Return format is handled by the output schema and row-limit semantics are in the query param doc. It is complete enough that an agent can call it correctly; a small gap is not stating pagination/limit behavior in the description itself, though the schema covers it.

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 description coverage is 100%, and both the query and canvas_id params carry thorough inline descriptions (including an SQL example and row-limit guidance), so the schema does the heavy lifting. The description adds marginal value by steering agents to obtain table/column names from fema_dataframe_describe before writing valid SQL, but this is a light bonus on top of an already-complete schema — baseline 3.

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?

States a specific verb+resource ('Run a read-only SQL SELECT against a DataCanvas table') plus its capabilities (aggregation, GROUP BY, SUM/COUNT, time-series). It names the staging tool (fema_search_nfip) and the prerequisite (fema_dataframe_describe). It implies a distinction from fema_query_dataset via 'without re-fetching from the API', but never explicitly differentiates itself from that closest sibling, which is the main gap.

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?

Clearly defines the use case: local analytical queries over the full NFIP result set without re-fetching, and mandates a call sequence ('Call fema_dataframe_describe first'). What's missing is an explicit when-NOT-to-use statement or named alternative — for instance, when to prefer fema_query_dataset over querying the staged local table is left to inference.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description reinforces and expands on these by stating that it returns 'every county/municipality designated under the declaration' – aligning with the openWorldHint (complete results) – and lists the specific data returned (programs activated, incident period, state info). It adds meaningful behavioral context beyond the annotations, with 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?

Three sentences, each earning its place: the first states the action and parameter, the second describes the return content, and the third provides routing guidance. The most critical information (what it fetches) is front-loaded. No fluff or repetition.

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 the presence of an output schema, the description does not need to detail return formats, but it still summarizes the key return elements. It explains how to obtain the required parameter and how the result chains to other tools. For a read-only single-parameter fetch with annotations covering safety and completeness, nothing essential is missing.

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%, so the input schema fully documents the single parameter, including its type, example, and source. The description repeats the example and the source ('Use fema_search_disasters to find disaster numbers') without adding any new semantic meaning for the input parameter itself. The chaining mention relates to the output, not the input. Thus the baseline of 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 states a specific verb ('Fetch'), a resource ('designated-area rows'), and a specific identifier ('disaster number'), making the purpose unambiguous. It clearly differentiates from siblings like fema_search_disasters (search vs. fetch) and the assistance tools (general details vs. specific assistance programs). No other tool does exactly this.

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 tells the agent to use fema_search_disasters to find disaster numbers, providing a clear path for obtaining the required input. It also indicates that this tool is the entry point for further chaining to fema_get_public_assistance and fema_get_housing_assistance, which helps the agent choose the right tool for follow-up queries. This is explicit when-to-use guidance.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering safety and external data variability. The description adds behavioral context about the returned data structure (county/ZIP breakdowns, specific data points) without contradicting annotations, so it earns a solid score.

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?

The description is two sentences, front-loads the primary purpose, then adds return details and usage hints. Every clause carries weight with no redundancy or filler, making it efficient and easy to parse.

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 the presence of an output schema and 100% parameter schema coverage, the description covers key inputs and usage hints well. It omits explicit pagination behavior (limit/offset), but these are defined in the schema, so the description is adequately complete for calling the tool.

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%, so baseline is 3. The description goes beyond schema by explaining how to use type (select owners/renters/both) and where to get disaster_number, adding meaningful guidance that helps the agent call correctly. This justifies a 4.

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 retrieves Individual Assistance (IA) housing data by disaster number, and enumerates the returned data (owner/renter breakdowns, IHP amounts, repair/rental amounts, inspection data). This specific verb+resource distinguishes it from siblings like fema_get_public_assistance, which focuses on a different assistance type.

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 tells the agent to source disaster_number from fema_search_disasters and to use type for selecting owner/renter scope. However, it does not mention alternatives or when not to use this tool (e.g., public assistance vs housing), leaving some inference to the agent.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds meaningful contextual behavior: it explains that PA projects exist only when the PA program is declared, which is a non-obvious condition that affects result availability. It also clarifies the output's focus on obligated amounts. 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 sentences total: the first states purpose and return fields, the second gives selection guidance, the third adds a scoping condition. Every sentence earns its place, no fluff, front-loaded with the core action.

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?

With an output schema present and all parameters documented, the description fills the remaining gaps: when to use this tool vs alternatives, the mutual exclusivity constraint, and the PA declaration prerequisite. Nothing an agent needs to call it correctly is missing.

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% with per-parameter descriptions, yet the description adds the critical constraint that exactly one of disaster_number or state must be provided (a mutual exclusivity not encoded in the schema) and explains the intent of each selector. This is substantial added meaning beyond the 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?

The description states a specific verb ('Retrieve'), a resource ('Public Assistance funded project records'), and its scope ('for a disaster or state'). It lists the returned fields and clearly differentiates from siblings by naming fema_search_disasters and explaining the PA program condition. This is 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 says 'Either disaster_number or state must be provided' and gives when-to-use guidance for each parameter: disaster_number to scope to a single declaration, state to browse all projects. It also notes the prerequisite that PA must be declared (pa_declared: true), which is a key usage constraint.

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

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

Annotations already provide readOnlyHint and openWorldHint, but the description adds valuable behavioral disclosures: the exact error returned for unknown dataset names, the timeout risk with NFIP queries, and the need for case-sensitive entity names. This goes beyond what annotations convey, giving agents critical operational knowledge.

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?

The description is moderately long but every sentence carries actionable information: purpose, examples, specific tips, and error behavior. It is front-loaded with the primary purpose and then provides necessary caveats. Slightly longer than ideal, but no fluff.

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 the tool's generic nature, the description covers all critical operational aspects: what it does, when to use it, dataset-specific gotchas, error behavior, and performance warnings. The output schema exists, so return values are documented. Nothing essential is missing for a correct call.

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 description coverage is 100%, so the schema already documents all six parameters with clear descriptions and examples. The description adds minor context like the propertyState nuance for filters, but this is more about data model quirks than the parameters themselves. No significant new meaning is added beyond the 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?

The description states a specific verb (query), resource (any OpenFEMA v2 dataset), and clearly positions it as the 'escape hatch' for datasets not covered by convenience tools. It lists concrete dataset examples and distinguishes it from the specialized siblings by framing it as the generic fallback.

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 tells when to use this tool ('datasets the convenience tools do not cover') and provides dataset-specific guidance, such as using propertyState for NFIP Policies and always including a county or ZIP filter to avoid timeouts. It also warns about case-sensitive dataset names and the unknown_dataset error.

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

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

Annotations already mark the tool as readOnlyHint and openWorldHint. The description adds behavioral context: deduplication of disaster numbers with designatedAreaCount, and that date filters apply to declaration date. This goes beyond the annotations and clearly sets expectations for return shape and filter behavior.

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?

The description is efficient, about 110 words, with every sentence contributing. It front-loads the main purpose and filters, then explains deduplication, chaining, and alternative usage. No filler or unnecessary detail.

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 the tool has 8 parameters, a comprehensive schema, annotations, and an output schema, the description covers all necessary aspects: purpose, filters, deduplication, chaining, and alternative usage. It does not need to restate return values since an output schema exists, but it still mentions designatedAreaCount as a useful detail.

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 description coverage is 100%, so the schema fully documents each parameter. The description adds value by clarifying the declaration_type meanings (DR, EM, FM) and describing the deduplication behavior, though some parameter descriptions are repeated from the schema. Overall it enriches understanding without redundancy.

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 states a clear verb ('Search') and resource ('federal disaster declarations') with specific filter dimensions (state, incident type, declaration type, date range, county). It distinguishes itself from fema_get_disaster by noting this returns summaries and that fema_get_disaster retrieves all designated-area rows for a specific declaration.

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?

Provides explicit when-to-use and when-not-to: says to use fema_get_disaster for full designated-area rows, explains the chain key usage for related tools, and clarifies declaration_type values (DR, EM, FM). Also notes date filters apply to declaration date, guiding appropriate filter semantics.

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

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

Annotations already declare readOnlyHint and openWorldHint. The description adds important behavior beyond annotations: the staging of full results on a canvas when DataCanvas is enabled, the inline preview limit behavior, and the prohibition of unfiltered access. This gives the agent a clear mental model of result delivery and constraints without contradicting the annotations.

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?

The description is 3 sentences, well-structured: first states purpose, second imposes constraint, third explains canvas behavior and alternatives. Every sentence earns its place; it is concise without omitting critical workflow details. Slight length is justified by the complexity of the canvas integration.

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 essential workflow: required filters, output fields, canvas staging for large results, and how to interact with staged data. Given the output schema exists and annotations cover safety (readOnly), there is no major missing context. It does not explain pagination or error handling, but these are typically implicit and not critical for a search tool.

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% with detailed descriptions for every parameter (limit, state, year_to, zip_code, canvas_id, year_from, county_code). The description reinforces the mandatory state requirement and explains the rationale (2.7M rows), but does not add new parameter semantics beyond what the schema already provides. Baseline 3 is appropriate since schema does the heavy lifting.

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 searches NFIP claims data with specific filters (state, county, ZIP, year range) and lists the output fields (claim counts, amounts paid, flood zones, loss years). It is distinct from sibling tools by focusing specifically on NFIP claims, and the required state filter is highlighted.

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?

Provides clear context on when to use the canvas workflow (when DataCanvas is enabled and results exceed inline preview), explicitly directing the agent to fema_dataframe_query for aggregation and fema_dataframe_describe for schema inspection. It states the mandatory state filter due to dataset size, but does not explicitly compare with other FEMA dataset tools, though the NFIP focus is implicitly exclusive.

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