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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds valuable behavioral context beyond that: 'Results are ranked exact-name-first, then by population' and that non-curated countries 'searches the bulk GeoNames tier.' These behaviors are not present in the annotations or schema, so the description meaningfully enhances transparency without contradicting anything.

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 three sentences, front-loaded with the core purpose, then layered with usage guidance, ranking behavior, and country restrictions. Every sentence adds distinct value—no filler or repetition. It is compact yet comprehensive, ideal for an agent to parse quickly.

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 read-only search tool with no output schema, the description covers all essentials: what it searches, ranking order, the exact relationship to a sibling (same records as lookup_postal_code), and the country-tier nuance. An agent can confidently call this tool with the right parameters and interpret the result, given the reference to lookup_postal_code. Nothing critical 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 description coverage is 100% (all three parameters have descriptions). The description adds contextual meaning beyond the schema: it explains that 'query' can be a place name or postal-code prefix (though the schema says this too), and critically provides guidance on when and why to use 'country' ('names repeat across countries'), which is not in the schema. This extra behavioral nuance justifies a 4 rather than the 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?

The description clearly states the tool's purpose: 'Find localities by name, city name, or the beginning of a postal code.' It uses a specific verb ('find') and resource ('localities'), and explicitly contrasts itself with lookup_postal_code by noting it handles partial codes and names. It also differentiates from nearby_places by focusing on postal-code association rather than proximity. This makes its role 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?

Provides explicit when-to-use guidance: 'Use this when the user gives a place name and wants its postal code(s), or has a partial code.' It also offers a clear alternative: 'Returns the same full records as lookup_postal_code,' implying that for exact code lookup, the sibling should be used. Additionally, it instructs to restrict with 'country' whenever known and explains the rationale (name repetition), plus notes the bulk tier behavior for non-curated countries. This fully equips an agent to select the right tool.

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