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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces rather than contradicts them ('opens nothing by itself'). It adds useful behavioral detail beyond the annotations: what the return contains (screens, buttons, fields) and that execution happens through a separate browser toolchain. It is silent on what happens if the app UI differs from the returned steps.

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?

The core flow is front-loaded correctly: what it returns, then that it doesn't act, then which tools to use. But the sentence is overstuffed with asides — the ChatGPT/Claude/any-AI-agent name-drop, the 'checked 25 Oct 2026' timestamp, and the official-API disclaimer — that dilute the two facts an agent needs.

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?

There is no output schema, and the description does cover the return shape (step-by-step screens/buttons/fields), which is the main gap it needed to fill. However, with zero input parameters it leaves unexplained how the recipe and meal plan target are conveyed at all, which an agent must resolve before it can act on the returned steps.

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?

The tool takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate at the parameter level. Baseline 4 applies. The more consequential omission (how the target recipe and meal plan are identified at all) is a completeness issue rather than a per-parameter one.

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 explicitly states the tool returns step-by-step instructions for adding a recipe to a meal plan in AnyList (screens, buttons, fields) and identifies itself as a guidance tool, not the actor. That distinguishes it from the cotlet_browser_* siblings it names. It stops short of 5 because the name/title promise an action ('Add recipe to meal plan') that the description then walks back, which costs an agent a beat.

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?

'opens nothing by itself; then do it with the cotlet_browser_* tools in the user's AnyList Cloud Browser' gives a clear handoff and sequencing rule. It also preempts the obvious alternative (calling AnyList's API) by stating none exists. It never says when to prefer this over sibling anylist_create_recipe or anylist_add_list_item.

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