Search places and addresses

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), and the description adds real behavioral context beyond them: proximity ranking ('Results near the given point rank first'), the Tehran default when lat/lng are omitted, and recovery guidance for empty result sets. It stops short of stating result ordering guarantees or paging behavior, but the added context is substantive.

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?

Front-loaded with the core action and scope in the first sentence, then organized by concern (geocoding, proximity, types, alternatives, empty-state). Dense but nearly every clause carries information; the run-on sentence listing `type` values and chaining targets is the only place readability suffers.

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 no output schema, the description does explain what results contain (coordinates, address, `id` for bl_place, `category` slug for bl_nearby), which is exactly the missing piece. The `type` parameter that appears only in prose is the notable hole — either the schema or the description is out of sync, leaving the agent unsure how to narrow by result kind.

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 100%, so the four real parameters are already documented, but the description describes a `type` parameter ('poi, road, city, region or category') that does not exist anywhere in the input schema. That is actively misleading — an agent may attempt to pass `type` and fail validation. The ranking semantics of lat/lng and the Persian/English query guidance are useful additions, but the phantom parameter drags this down.

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?

States a specific verb and resource ('Search Balad ... for places, streets, neighbourhoods and cities by name') plus the return payload (coordinates and address). It also names what it is not — bl_nearby for exhaustive POI sweeps and bl_reverse_geocode for the inverse operation — so an agent can separate it from siblings without opening a 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?

Gives two explicit use cases (find a named place; geocode an address/city), an explicit exclusion routed to a named sibling ('For every pharmacy, restaurant, etc. around a point use bl_nearby instead'), a fallback for empty results, and a chaining hint (pass lat/lng from a first bl_search when searching outside Tehran). Nothing is left to inference.

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