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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds useful context the annotations do not: that results carry sold-out/hidden flags and per-branch prices, and that omitting search terms yields a full listing rather than an error. It does not mention pagination behavior or how the default limit of 30 interacts with a full listing.

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 no filler, and the fallback behavior is packed into the second clause. The opening sentence leads with a bare field list rather than the tool's action, which makes it slightly less front-loaded than it could be.

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 five all-optional parameters, no output schema, and annotations already covering the safety profile, the description carries the remaining weight well by describing the shape of returned items and the no-filter default. Nothing an agent needs to invoke it correctly appears to be 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%, so every parameter (cafe, branch, limit, query, category) is already documented in the schema, setting the baseline at 3. The description adds only the combination rule — that query and category are optional and omitting both lists the menu — but says nothing about how branch and cafe interact or how results are ordered.

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 names the resource (menu items) and enumerates the fields returned — category, price, menu status, sold-out/hidden state, branch prices, allergens, dietary tags — then states the two search modes ('words in the name or description' or 'category'). This is concrete enough to distinguish it from write-side siblings like add_menu_items or set_item_sold_out, though it never explicitly frames itself as a read/search tool in a leading verb phrase.

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?

It gives clear call conditions: search by name/description text, by category, or omit both to list the whole menu — an explicit default path an agent can act on. It stops short of naming alternative tools or stating when-not to use this (e.g., to modify prices or mark items sold out, use a different sibling).

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