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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds value beyond these by disclosing the aggregation behavior ('in one call'), the precise set of geographies returned, and that each result includes its GEOID. No contradiction with annotations exists; the description augments them with useful behavioral detail.

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 compact: one dense sentence establishing the core function and result set, followed by a short routing directive. The geography-type list is long but earns its place because it tells an agent exactly what the tool covers. It is front-loaded with the main purpose before the preference instruction. Slight room for trimming, but nothing wasteful.

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 there is no output schema, the description compensates well by enumerating the geographies returned and noting each carries a GEOID. It covers the four parameters via the schema and the tool's routing via the usage line. The main gap is that the exact response structure (how the geographies are nested or keyed) is not specified, but for a geospatial stack tool this is a minor omission given the listing provided.

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 all four parameters (latitude, longitude, layers, service) are already documented in the schema with descriptions. Per the rubric, baseline is 3 when schema carries the load. The description adds marginal context by referencing that layer names must match tigerweb_list_layers exactly and noting the US-negative longitude convention, but it does not substantially expand on parameter meaning beyond what the schema already provides.

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 opens with a specific verb and resource: 'return every TIGER/Line geography containing it' given a lat/long, and enumerates the full scope of returned geographies (state, county, tract, block group, ZCTA, etc.) each with its GEOID. It is clearly differentiated from the sibling tigerweb_query and tigerweb_list_layers by stating it returns the entire stack 'in one call' and by the explicit routing instruction against web search. An agent can tell exactly what this does without opening the schema.

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 gives an explicit when-to-use condition: 'PREFER OVER WEB SEARCH when you have a coordinate and need the geography stack around it.' This is clear routing guidance for the most common alternative. It does not explicitly contrast with the sibling tigerweb_query (which is a close relative), so the exclusion list is not fully complete, but the primary selection criterion is stated unambiguously.

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