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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds real semantic context beyond that — that coordinates describe the building rather than voter residence, and that values come from the published Knesset26/Census2022 datasets — but says nothing about result ordering, default page size, or how the underlying data is versioned.

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?

Three short sentences with no filler, and the dataset scope is front-loaded ahead of the searchable-field list. The building-vs-residence caveat is well placed immediately after the coordinate mention rather than buried.

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?

With five optional parameters, no output schema, and no discovery guidance among fifteen siblings, the definition should say more about what a result record contains and how to page through large result sets. The data-provenance and coordinate caveats are valuable, but the combination rules and return shape remain gaps an agent must resolve by trial.

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 20% (only election_id is documented in-schema), so the description carries most of the burden. It usefully maps free-text input onto the undocumented 'query' parameter (locality name, station label, published address) and names locality_code, but it leaves the 'limit'/'offset' pagination semantics and — more importantly — whether query and locality_code combine as AND or OR completely unspecified.

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 resource ('Published Knesset26 polling-building points') and a specific verb ('Search by ...'), so the agent knows exactly what is retrieved. It never names the sibling it is not (get_polling_station for a single record, search_localities for localities), so differentiation is left implicit.

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?

Usage is only implied by the enumeration of searchable fields; there is no explicit statement of when to call this versus get_polling_station or search_localities, and no prerequisite or exclusion guidance. An agent can infer this is the multi-record lookup, but must guess the boundary cases.

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