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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: results are the 'official published' building point and an 'independent census assignment', and boundary history is not interpolated. It still says nothing about missing/ambiguous records or how a station outside a locality is handled.

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 dense sentence with no wasted words, and the key caveat is front-loaded at the end of the clause. However, the density comes at the cost of clarity — 'CEC identity' and 'independent census assignment' are jargon that a non-domain agent may not parse on first read.

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?

There is no output schema, so the description's enumeration of returned fields (identity, address, result, census assignment) does useful work. But with two of three parameters undocumented and no guidance on ambiguity or empty results, it does not fully cover the complexity of a keyed lookup with a tricky ballot identifier.

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 only 33% — election_id carries a description (latest / k26 / full date, with a warning that a bare year is ambiguous), but ballot_label and locality_code are undocumented in both schema and description. The description gives no hint of what a ballot_label is or how locality_code relates to the CEC identity, so the agent must guess on two required parameters.

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 the specific resource ('One station') and enumerates the returned facets: CEC identity, official building point/address, aggregate result, census assignment. Implicitly contrasts with the list-oriented sibling search_polling_stations by emphasizing a single station. It lacks a leading verb, but the entity and payload are 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?

No explicit when-to-use guidance and no routing to search_polling_stations for lookup-by-name scenarios. The only scoping statement is 'historical positions are not inferred', which constrains interpretation but does not tell the agent when this tool is the right choice versus alternatives.

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