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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the search-only, fixed-corpus nature is covered by structured data. The description adds genuine context by naming the returned fields (page link, address, opening hours, what they make) and the curation qualifier 'hand-checked'. It says nothing about result ordering, pagination, or how lat/lng and area interact when both are supplied, which is the behavioral detail an agent would still want.

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, front-loaded with the corpus definition before filters and return values. Every sentence contributes new information and there is no filler or repetition of the title.

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 eight optional parameters and no output schema, the description usefully compensates by describing the return shape and the scope of the dataset. It is nearly complete for a search tool; the remaining gaps are ranking/pagination behavior and the interaction between the mutually redundant location parameters (area vs lat/lng vs radius_km).

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 all eight parameters are already documented with examples ('jp/tokyo/taito', 'leather wallet', defaults and maxima for limit/radius_km). The description's filter list restates those parameters rather than adding meaning, and it does not explain match semantics for query or precedence between area and lat/lng coordinates. Baseline 3 applies when the schema carries the weight.

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 concrete verb and resource ('Find hand-checked local makers on Pinmade: shops that design and make their own things ... with a place you can walk into'), which sharply bounds the corpus to physical, maker-owned shops. It also enumerates the available filters and the returned fields. The only gap is that it never names the siblings get_shop or list_places, so differentiation is left implicit from the search/filter framing.

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?

The description implies usage through its filter list ('Filter by words, category, place, distance and open now'), which tells an agent what the tool is for. It gives no when-not guidance and never routes the agent toward list_places for discovering valid area paths or get_shop for a single shop, so an agent must infer the boundary from tool names alone.

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