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

Adds genuine context beyond annotations: the draft is private, it is a write blocked on read-only accounts, and it discloses the return shape {id, title, servings, assumed, optional_question, next} since no output schema exists. However, it is silent on whether re-invoking creates duplicate drafts (annotations already say idempotentHint=false) and on what `assumed` contains, leaving the mutation-safety story to the annotations.

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?

Four sentences, front-loaded with the purpose, then routing, then the return contract. No sentence is decorative — even the parenthetical about read-only accounts is an actionable constraint.

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 no output schema the description supplies the return fields and the `next` handoff, and with a 6-parameter schema all documented it leaves nothing material unexplained for a non-idempotent create call whose destructiveHint is already declared false.

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 every parameter carries a descriptive string with examples, so the schema carries the load. The description adds only indirect meaning (servings appears in the return, "assumed" hints that unspecified fields are filled in) and never explains diet/cuisine/flavor_direction semantics, so 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+resource ("Invent a new recipe") and narrows it to a dish the user named, which separates it from save_recipe and suggest_dishes by name. An agent can pick it without opening the schema.

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 explicit routing: vague idea → suggest_dishes, existing text → save_recipe, and the follow-on chain update_recipe then finalize_recipe. It also constrains interaction behavior ("Ask at most ONE short question"), which is a real usage rule rather than a restatement.

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