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

Annotations already declare read-only, idempotent, open-world, non-destructive. The description adds genuinely new behavior: pagination with `has_more`, that a single response is only part of the menu, and that it renders as cards with category tabs and Prev/Next when the host supports MCP Apps. These are traits not conveyed by annotations or schema.

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-loads the core purpose and required id, then layers mode guidance and caveats. Slightly dense at five sentences, but each earns its place; minor redundancy between the pagination note and the query-reliability note.

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 paged, mode-switching tool this covers the key completeness gaps: pagination limits, how to find a specific item, and host-dependent rendering. With an output schema present, it rightly omits return-field details.

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, but the description adds real semantic relationships: `categoryId` comes from the result's `categories`, `query` searches the entire menu across pages and sections, and `page` interacts with `has_more`. This goes beyond field-level docs, though it doesn't cover `city` or `language` 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?

States a specific verb and resource ('Show the menu for a merchant/restaurant') and identifies the required key (merchant_id from a `search` result). It is clearly distinguishable from siblings like `search`, `get_product_details`, and `get_full_menu` by being a per-merchant, paged menu view.

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?

Explicitly tells the agent how to choose modes: pass `categoryId` to browse a section, omit both to show top items, provide `query` to search within the menu. It also names the recommended alternative for item lookup (`query="<item name>"` instead of paging), which is exactly the when-to-use guidance an agent needs.

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