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

Adds real behavioral context beyond the annotations: the returned link is personal, single-use, expires in 30 minutes, and leads to a user-facing page where the human picks which chats upload and sees how many are already imported. That human-in-the-loop handoff is exactly the kind of detail annotations can't carry. It doesn't cover what happens when the link expires or when it should be re-issued.

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 the core behavior (the link and its constraints) before the usage trigger. The first sentence is a long, dense clause chain covering constraints, page behavior, and import counts, but every element carries real information and nothing is filler.

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 zero-parameter tool with no output schema and readOnly/openWorld annotations already set, the description covers the trigger, the prerequisite skill, the returned artifact, its expiry, and the user-side flow. The only gap is post-expiry behavior, which is minor given the tool's simplicity.

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 no parameters, so the schema imposes no documentation burden and the description needs no param semantics. The mention of "cuántos tiene ya importados" describes return content rather than an input, so it adds no parameter information but isn't required to.

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 concrete verb and resource: it hands back a single-use personal link to an import page for ChatGPT or Claude chat exports. It implicitly separates itself from the read-oriented siblings (list_chats, read_chat) by framing the action as importing/uploading into MemoryBrain. It doesn't name a sibling explicitly, which keeps it just short of a 5.

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?

"Úsala cuando quiera importar o pasar sus chats a MemoryBrain" gives a clear trigger condition, and "Antes, carga la skill importar-chats con get_skill" states a prerequisite in correct order. It stops short of naming when NOT to use it or which alternative applies (e.g. list_chats for just viewing), so no explicit exclusions.

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