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

Adds real behavioral context beyond the annotations: changes hit 'the live shop at once' and there is 'an Undo in Design,' which tells the agent the blast radius and the recovery path. It does not cover failure behavior (e.g. whether an invalid item aborts the whole write) or any permission requirements, keeping it below a 5.

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 short sentences, each earning its place: first the action and intent, then the required read-first workflow, then the operational consequence. The most decision-relevant information is front-loaded.

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 single-parameter mutation with no output schema, it covers what is replaced, that the change is immediate on the live shop, and that it is recoverable. It leaves out what the response contains and how validation errors are surfaced, which are the remaining gaps for an agent invoking it cold.

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% and the nested item properties are already documented thoroughly in the schema, so the schema does the heavy lifting. The description reinforces the replacement semantics of the 'items' array but adds no syntax, ordering rules, or handle-format detail beyond what the schema and its field descriptions already state.

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 ('Replace the header menu') and enumerates the intents it serves (rename, reorder, add, remove items). An agent can distinguish it from the sibling get_menu at a glance, since this tool is described purely as the whole-menu replacement.

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?

Gives an explicit prerequisite workflow: 'Read get_menu first and send the whole menu back changed,' which routes the agent to the read sibling and defines the read-modify-write pattern. The whole-menu-replacement constraint also implicitly rules out partial edits, which is the key usage decision here.

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