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

Annotations already declare this is a safe read (readOnlyHint, destructiveHint false), so the description's job is lighter. It adds real value beyond them by disclosing a dependency chain ('menu_item_id values returned are required by create_lunch_order_draft'), which an agent needs for correct sequencing.

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 front-loaded sentences with no filler. The scope and return contents come first, then parameter resolution, then cross-tool dependencies and alternatives.

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?

An output schema exists, so return-value detail is unnecessary, and the annotations cover the safety profile. The description fills the remaining gaps: filtering precedence, the create_lunch_order_draft dependency, and the alternative for placed orders.

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 baseline is 3. The description exceeds that by adding precedence and default semantics not stated in the schema: today is used when neither is given, and date wins if both are passed. This clarifies behavior the schema descriptions leave ambiguous.

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 ('Returns the orderable lunch menu for the user's active school') and enumerates what comes back (names, prices, dietary tags, remaining quantity). It is clearly distinguishable from create_lunch_order_draft and list_my_lunch_orders, which are named directly.

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 routes the agent: pass date for one day, month for a full listing, neither for today, and resolves the conflict ('if both are passed, date wins'). It also names the sibling to use for already-placed orders, so the when/when-not/alternative conditions are all covered.

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