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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context beyond them: data provenance and approximate coverage (~890 places from the city map plus confirmed restaurants), and what each result contains (bina.et page, phone only 'when known', sub-city, cuisine, map point). It omits any note on result ordering or what happens when limit truncates results.

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 with no filler, front-loading what the tool covers before the search/filter mechanics and the cross-tool handoff. Slightly dense in the final sentence, but every clause carries information.

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?

An output schema exists, so return values need not be spelled out; the description still summarizes them enough for planning. All four optional parameters are covered by the schema, and the description supplies provenance and coverage. Nothing an agent needs to call this correctly is missing.

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% and the schema already enumerates the sub-cities, the kind enum and gives query examples, so the baseline is 3. The description's 'search by name or cuisine word, filter by kind and sub-city' largely restates that mapping rather than adding syntax, defaults or edge-case behavior.

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?

Specific verb+resource (search restaurants/cafés/fast-food) scoped to Addis Ababa, with the data source named (bina.et/restaurants, ~890 places). An agent can distinguish this from siblings like search_places, search_hotels or search_pharmacies without opening any 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?

States the two intended search modes (by name or cuisine word) and the two filter axes (kind, sub-city), which is clear context for invocation. It also routes the agent onward (pass "lat,lng" to quote_ride), but never names a competing sibling tool such as search_places as the alternative to use when the query is not food-related.

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