RestoreWorth FEMA Data

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so this dimension is about added context — and the description adds a real one: missing source values are returned as "not in source", never 0, which prevents an agent from misreading absent data as a zero count. It also discloses the underlying source (FEMA open data) and the coverage window (declarations since 2000). What it does not cover is cost, latency, or aggregation freshness.

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 filler: the first front-loads the identity and the full contents of the profile, the second carries the single most important semantic caveat about the "not in source" sentinel. Every clause 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?

With no output schema, the description correctly shoulders the burden of explaining what comes back, and it does so by enumerating the data blocks plus the sentinel behavior for missing values. It is close to complete for a single-parameter read tool, though it says nothing about any not-found behavior for an invalid or unknown FIPS.

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 the single fips parameter already documents the 5-digit format, pattern and an example. The description only restates "one county by 5-digit FIPS", adding the one-county scoping but no new syntax, format or edge-case information, so baseline 3 applies.

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 resource (a FEMA open-data profile of one county keyed by 5-digit FIPS) and enumerates the exact payload components: NFIP paid claims, disaster declarations since 2000, IHP inspections, Community Status Book and CRS classes. That breadth implicitly separates it from the narrower sibling nfip_claims_by_county, but no sibling is named, so sibling differentiation is left to inference.

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?

There is no explicit when-to-use guidance, no when-not-to-use, and no alternative tool named. The only usage signal is that one FIPS maps to one county; an agent must infer from the sibling list whether this supersedes nfip_claims_by_county or complements it.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds meaningful non-safety context: the data provenance window, the definition of the metric, and the crucial methodological caveat that the returned figure is the band median rather than a prediction for a specific property.

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 tightly packed sentences that front-load the metric and scope, then immediately qualify the optional branch and its interpretation limit. No filler; every clause carries either provenance or interpretive guidance.

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 no output schema, the description carries the return-value burden and does so by defining the ratio, the dollar-value variant, and the interpretation caveat. It stops short of describing anything about the depth bands themselves (e.g., how in-between depths resolve), a minor remaining gap.

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 baseline would be 3, but the description goes beyond the schema for building_value_usd by explaining its effect (returns ratio × value) and warns that the output remains a band median, not a home-specific estimate. The depth band and segment parameters are only echoed, not deepened.

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 names the exact metric returned (median damage ratio of FEMA actual cash value of damage over building value), the source (NFIP paid claims 2015-2024), and the breakdown dimensions (interior water depth band, single-family one-floor segment). An agent can tell precisely what this produces without opening the schema, and it is unambiguously distinct from the claims-by-county/state siblings.

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?

Usage is implied through the building_value_usd branch (ratio alone vs. ratio times value) and the caveat that the result is a band median, not a per-home estimate. However, it never states when to choose this tool over the sibling tools (e.g., nfip_claims_by_county, county_profile) or any precondition for use.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value by disclosing exactly what content comes back (publisher, dataset page, terms, as-of/retrieval dates, publishing page), which is real behavioral context given there is no output schema. It does not mention ordering or size of the list.

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?

A single front-loaded sentence: verb, scope, then the field inventory. Every clause carries information; nothing is redundant or padding.

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 no output schema, the description is the sole source of return-value information, and it enumerates the fields well. Minor gap: it does not say how the list is ordered or how large it is, though for a static zero-param catalog this is a small omission.

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 tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate, and it correctly does not waste words on inputs.

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?

Specific verb ('Lists') plus a precisely scoped resource ('every source file this server reads'), with the returned fields enumerated. It is clearly a metadata/provenance tool, cleanly distinguishable from the sibling data-query tools (county_profile, nfip_claims_*).

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?

Usage is implied by the fact that it takes no parameters and returns a provenance catalog, but the description never states when to call it or how it relates to the sibling tools. No explicit 'use this when you need to cite/verify a data source' guidance, and no exclusions.

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 readOnly/idempotent/non-destructive/non-open-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the table only retains counties with at least 100 paid claims, misses fall back to the state row, and the response flags that substitution, plus a units caveat ('amounts paid by NFIP, not repair cost').

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, front-loaded with the resource and period before the input rules and the fallback caveat. Nothing is padding, though the two-period coverage phrase reads slightly compressed and the fallback sentence is dense.

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?

No output schema exists, yet the description covers the key output-behavior detail (absent counties return the state row and the answer says so) and the data-meaning caveat. It leaves return field names and units unspecified, which is a minor gap for a lookup 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 FIPS pattern, state length, and county naming are already documented there; the description largely restates the FIPS-vs-name+state choice. Its only added semantic is the implied pairing requirement (county needs state), which the schema also states. Baseline 3 applies.

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 and resource ('NFIP paid building claims for one county') with explicit coverage ('2015-2024 and 2020-2024'). The phrase 'for one county' implicitly separates it from the sibling nfip_claims_by_state, so an agent can route without opening schemas.

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 explains how to supply input (5-digit FIPS, or county name plus state) and what happens on a miss, but never states when to prefer this over nfip_claims_by_state or county_profile. Usage is implied rather than framed as a decision rule.

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 cover the safety profile (readOnly, idempotent, non-destructive), so the description correctly focuses on data semantics instead: the upstream source and version (FEMA OpenFEMA, NFIP Redacted Claims v3), the 2020-2024 coverage window, and the important caveat that figures are NFIP payouts rather than repair cost. It does not address data freshness, missing-state behavior, or auth, which keeps it short of a 5.

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, both load-bearing: the first front-loads scope, source and returned metrics in a compact colon list, the second carries the interpretive caveat. No filler or restatement of the title.

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 no output schema, the description compensates by naming the returned measures, and it supplies provenance, time coverage, and a semantic caveat. For a single-parameter read-only aggregate, an agent has everything needed to select and call 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% for the single 'state' parameter, which already documents both accepted forms (USPS code or full name). The description adds no syntax or validation detail beyond that, so the baseline 3 applies.

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 resource (NFIP paid building claims), an explicit scope (one US state or DC, 2020-2024) and enumerates the returned metrics (paid claim count, quartiles/median of amount paid, dominant flood event and share). The state-level granularity also implicitly separates it from the sibling nfip_claims_by_county.

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 stated scope ('for one US state or DC') makes the appropriate use case clear and pairs naturally against the county-level sibling. It does not, however, explicitly say when to prefer this over nfip_claims_by_county or the other siblings, so there is no exclusion guidance.

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