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

With no annotations supplied, the description must carry the behavioral burden. It usefully discloses that matching is fuzzy and that each match is returned as an MCP App card, but it says nothing about how results are ordered, what happens when nothing matches, or that results carry inspection history (implied only by the history_n parameter).

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?

Two tight sentences with the primary capability and its notable property (fuzzy spelling) front-loaded, followed by the one scoping nuance. Nothing is redundant or padded.

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?

For a five-parameter tool with no annotations and no output schema, the definition covers the search semantics but omits that returned cards include recent inspection history, which is the tool's distinguishing data and the reason history_n exists. Given inspection-focused siblings, that omission leaves the picture noticeably incomplete.

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%, so all five parameters are already documented, and the description only adds meaning for city scoping. It gives no extra intuition about threshold (higher = stricter), limit, or history_n, so the baseline of 3 applies.

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 ('looks up restaurants by name') plus the tolerance behavior (partial names, imperfect spelling) and the return form (an MCP App card per match). It is clear, but it doesn't distinguish itself from sibling find_nearby_restaurants, which an agent could plausibly confuse with a name search.

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 only routing hint is that the optional city argument narrows the search to one city, which implicitly contrasts with a proximity-based lookup. There is no explicit when-to-use versus find_nearby_restaurants or get_city_inspections, and no guidance on when to raise the fuzzy threshold instead of relaxing the query.

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