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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety bar is covered. Above that, the description discloses matching semantics (term-by-term across name, district, province, address), the fallback behavior when both filters are empty, and how returned fields map to recipient_destination_id and address. Return format and limit/pagination behavior are the remaining gaps.

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 tight sentences, front-loaded with the resource and the empty-query fallback before the search mechanics and the id mapping. Every sentence carries information; the only cost is a dense phrasing in the middle clause that packs four searchable fields into one line.

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, and the description partly compensates by describing what comes back: province names with record counts in the empty case, and a record with an id plus address fields otherwise. For a four-parameter search tool with annotations covering safety, the only real gap is undocumented limit/category behavior.

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 50% (q and city documented, limit and category not), so the description must compensate — and it does for the two important ones: it explains that q matches word-by-word across four fields with an example ('silivri kadın') and that city is a province filter. It adds nothing about limit or the category enum values, which are self-explanatory but unstated.

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 names the concrete resource set (prison / military unit / institution catalog) and describes the search behavior, so an agent knows this is a lookup tool over a destination catalog. It does not use an explicit verb in the first sentence (the verb 'ara' lives only in the title), and it never names a sibling, but the resource is specific enough to separate it from the letter tools.

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?

It gives a concrete conditional: when city and q are empty it returns the province list with record counts, otherwise it does a term search. It also states the downstream contract — the returned id is used as recipient_destination_id — which tells the agent where this fits in the letter flow. It stops short of explicit when-not-to-use or naming an alternative tool.

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