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

Annotations declare readOnlyHint, openWorldHint, and idempotentHint, covering safety and idempotency. The description adds non-obvious behavior: 'The upstream endpoint is not paginated — it returns every matching area in one response — so this caps client-side. A nationwide county query matches over 3,000 areas.' This alerts the agent to response size and limit semantics, which is value beyond the annotations. No contradiction exists.

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 four sentences with no redundant phrasing. The main purpose is front-loaded, followed by use cases, a critical input format warning, and a usage tip. Every sentence earns its place, and the structure is easy to scan.

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 tool has 5 parameters, a nested filters object, and an output schema (not shown but indicated). The description covers typical applications, the non-pagination behavior, and the prerequisite of FIPS resolution. It does not describe return value shape, but the output schema covers that. For a moderately complex aggregation tool, this is complete enough; a 4 reflects minor gaps like missing explicit notes on combining filters.

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. The description compensates further by explaining the FIPS/abbreviation constraint for geographic filters and pointing out the limit's client-side capping behavior with a concrete scale example. This adds practical meaning beyond the schema's per-field descriptions, particularly for the filters object.

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: 'Aggregate federal spending by state, county, or congressional district.' This clearly distinguishes it from sibling tools like spending_by_category (categories) and spending_over_time (time series). The resource and granularity are explicit, leaving no ambiguity about what the tool does.

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 provides clear use case guidance ('per-capita analysis, regional comparisons, and mapping federal investment patterns') and instructs on prerequisite steps ('Resolve place names to FIPS codes using a geocoding server'). It does not explicitly name alternative tools or state when not to use it, but the context is strong enough to guide an agent. A 4 is appropriate because it offers actionable usage conditions without explicit exclusions.

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