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

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, and the description restates those — redundant but harmless. The genuinely additive disclosure is the operational envelope: 64 KB JSON input ceiling, 1 s per call, 1 MB result cap, plus an explicit determinism guarantee, which no annotation encodes.

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?

Each block is front-loaded and labelled (purpose, Cuándo, No para, Efectos secundarios, Determinista, Límites), with zero filler sentences. The full ES/EN duplication doubles the length, which is a real cost even if it is a house convention.

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?

Output shape is partly pre-empted (the eight named neighbors) and an output schema exists for the rest, so no return-value explanation is owed. With one parameter, full annotation coverage and explicit limits, an agent has everything needed to call this correctly on the first try.

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% with a single required string parameter and an example, so the schema carries the load and the baseline applies. The description only implies the precision-preservation rule ("de la misma precisión") without describing input validation or the meaning of the 1–12 char bounds beyond the schema.

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?

Names a specific verb and resource ("Devuelve las 8 celdas geohash vecinas de la misma precisión") and enumerates the exact directional set returned (n, ne, e, se, s, sw, w, nw). It explicitly contrasts with the closest sibling, geohash-decode, so an agent can pick between them without opening either 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?

Provides an explicit "Cuándo" clause, a "No para" exclusion, and names the alternative tool (geohash-decode) by name. The when-clause is somewhat generic — mentioning distances, bearings and areas that this tool does not itself compute — which slightly blurs the targeting, but the front-loaded "para búsquedas por cercanía" recovers it.

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