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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: the tool returns procedural content and performs no navigation or mutation, which prevents the agent from assuming the favourite is already applied. It omits whether the returned procedure requires the Cloud Browser session to be pre-opened and whether the caller must already know the target title.

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 behavior and the hand-off to cotlet_browser_* tools are front-loaded and useful. The closing sentence about AniList's free public GraphQL API and the absence of an official MCP server as of '17 Oct 2026' is provenance trivia that does not help an agent decide or invoke, and it dilutes an otherwise two-sentence definition.

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 parameters and no output schema, the description does the necessary work of describing the return value as step-by-step screens, buttons, and fields. However, a zero-parameter tool cannot know which title to favourite, and the description never explains that the caller must supply or already know the target title before following the guide — a meaningful gap for correct use.

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, so the baseline is 4. The description adds nothing about parameters because there is nothing to describe, and the empty schema correctly signals the tool accepts no input.

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 states a specific resource and outcome: it returns step-by-step instructions (screens, buttons, fields) for favouriting a title in the user's own AniList account, and explicitly says it 'opens nothing by itself'. That separates it from the cotlet_browser_* siblings that actually perform the action. It loses a point because the title 'Favourite a title' reads like a mutation and the description has to spend a clause undoing that impression.

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?

It gives a clear two-step routing: call this to get the procedure, then execute it with cotlet_browser_* tools in the user's AniList Cloud Browser. It does not address the neighbouring anilist_rate_anime_or_manga, anilist_update_list_entry, or cotlet_app_guide, so the agent gets no guidance on when one of those already covers the same need.

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