Address to Census Tract MCP

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, and the description reinforces this with "No network call," which is useful confirmation of the parse-only behavior. It goes further than the annotations by describing the decomposition of the return value, though it says nothing about error behavior for malformed or unsupported lengths.

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?

One dense sentence that front-loads the action and output fields with no filler. The nested parenthetical list of length mappings makes it slightly harder to scan than a two-sentence layout would, but nothing is redundant.

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 carries the burden of explaining the returned components, and combined with the annotations it covers safety and network posture. The only gap is failure modes for invalid GEOIDs, which is minor for a pure parsing utility.

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 baseline is 3, but the description adds real meaning beyond the schema by decoding GEOID length variants (2 state, 5 county, 11 tract, 12 block group, 15 block) and the 1400000US prefix form. That tells the agent which inputs are actually valid, which the max/min length constraints alone do 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?

States a specific verb-and-resource pair ("split a census GEOID") and enumerates exactly what the split yields: state and county FIPS, tract code, displayed tract number, block group, block. This is unmistakably distinct from the siblings, which are address/coordinate lookups rather than GEOID parsing.

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 rather than stated: an agent can infer it should call this when it already holds a GEOID and needs its components. There is no explicit when-not guidance and no mention of the sibling tools as alternatives, though the difference is obvious from the verb.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real value by enumerating the returned fields (GEOID, block group, FIPS, districts, urban area) since there is no output schema. It does not disclose failure behavior when an address fails to match or any rate limits, so it only partially goes beyond 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?

Front-loaded with the core action and source, followed by a return-field inventory and use cases, with no filler. The return-field list is long but earns its place given there is no output schema.

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 two-parameter read-only lookup with no output schema, the description covers what the tool does, what it returns, and when to reach for it. The remaining gap — no-match/error behavior and precision caveats on geocoding — is minor but leaves the definition slightly incomplete.

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 address formatting and the vintage enumeration are already documented with an example in the input schema. The description adds no meaning beyond that, such as whether 'current' vintage is the default or what the vintages are for — 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 (look up) and resource (census tract) for a US street address, and names the authoritative source (US Census Bureau Geocoder). The sibling get_census_tract_for_coordinates is implicitly distinguished by the address-vs-coordinates input, so an agent can pick between them 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?

The closing sentence gives concrete use cases (CRA, LIHTC, opportunity zones, grant eligibility, demographic lookups) which is clear positive guidance. It never explicitly says when NOT to use it or names get_census_tract_for_coordinates as the alternative for coordinate input, so it stops short of a full when/when-not statement.

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, openWorld, and non-destructive, so the safety profile is covered. The description adds the underlying data source and the fact that multiple geography levels come back in one call, but omits failure modes (out-of-coverage points, geocoder outages) and any rate-limit context.

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 efficient sentence that front-loads the returned geographies and closes with the data source. The enumeration of geography types is slightly long but each item carries informational value about the response.

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 does a reasonable job listing what is returned, and the schema handles all parameters. It still leaves the US-only coverage assumption and error behavior unstated, which matters for a geocoding lookup that fails silently outside Census coverage.

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 latitude, longitude, and the vintage enum are fully documented in the schema. The description adds no extra meaning about coordinate precision, US-only constraints, or how vintage selection affects returned geographies, 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?

The description names the resource concretely (census tract, block group, block, county, place, congressional and state legislative districts) and the input (latitude/longitude), plus the upstream source (US Census Bureau Geocoder). It implicitly separates itself from get_census_tract_for_address by keying on coordinates, but never names the sibling.

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?

No explicit when-to-use or when-not-to-use statement. An agent can infer the coordinate-based branch of the sibling pair, but nothing tells it to prefer get_census_tract_for_address when an address is available, nor what happens for non-US or ocean coordinates.

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