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

Annotations declare readOnlyHint=false, and the description explains why: reading a pre-sign-in draft 'attaches it to that account' once the user links — a real side effect no annotation conveys. It also discloses that reads follow revisions of that exact draft and what happens when a draft is unavailable.

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-loaded with what is returned, then usage, then edge cases; no sentence is filler. It is five dense conditional sentences, though, so the structure is efficient rather than maximally tight.

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?

Covers the hard cases an agent would otherwise get wrong — pre-sign-in drafts, account linking, unavailable drafts and their recovery route, and the draft/Saved Week/This Week boundary. An output schema exists, so the description carries no obligation to detail return shape.

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 schema already explains both menuDraftId and configurationId, including the omit-only-when-reading-by-configurationId rule. The description only loosely implies when menuDraftId is unreliable ('latest menuDraftId is uncertain') and adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 current state of a menu draft') and enumerates the payload (slots, labels, choices, selection/lock state, servings, slotIssues). It also explicitly separates the resource from its look-alikes: 'Drafts are separate from Saved Weeks and This Week.'

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 three concrete trigger conditions ('before an edit, after the user has chosen dinners in the widget, or whenever the latest menuDraftId is uncertain') and an explicit alternative path: unavailable drafts are recovered through open_saved_week with the known savedWeekId, otherwise the user reopens the week.

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