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

With no annotations, the description carries the full burden. It does disclose a genuinely important behavioral trait: the server ranks a wide recent window and then serves one page of that ranking, so offset paging is over a stable global order rather than a per-page re-sort. It leaves gaps, though — the length of the 'recent window' is undefined, and there is no statement of whether the result is cacheable, rate-limited, or how the card is rendered.

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 core behavior and followed by the pagination contract; nothing is redundant. Minor cost is the unexplained 'MCP App card' jargon, which assumes the reader knows the rendering model.

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 three-parameter read tool with a fast, simple contract, the description covers purpose, ranking semantics, and pagination adequately, and the schema already documents next_offset. The main missing piece is what the returned card actually contains and how far back 'recent' reaches, which matters because no output schema is provided.

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 baseline is 3, and the description adds real meaning on top: it establishes that limit/offset page through a pre-computed ranking, which is exactly the semantics an agent needs to reason about offset stability. It does not add anything beyond the schema for the enumerated city list, which is fine since the enum already constrains it.

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 gives a precise verb and resource ('Returns an MCP App card ranking restaurants with the most serious recent health-inspection violations') plus the scope of supported cities, which clearly separates it from a generic restaurant search. It stops short of naming the overlapping siblings (get_milwaukee_inspections, show_inspection), so the agent must infer the boundary itself.

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 ranking/leaderboard framing implies when to reach for this tool over search_restaurants or find_nearby_restaurants, but there is no explicit when-to-use or when-not-to-use statement. There is also no guidance on how it relates to get_milwaukee_inspections, which appears to cover a subset of the same cities.

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