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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with "No guarda nada" (persists nothing) while adding scope information the annotations lack: the result is tied to this specific chat, not the whole account, and the response includes note and project counts. Rate limits, caching, or how a disconnected state is reported are not addressed, keeping it below a 5.

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?

Three short sentences in a clean progression: what it returns, when to invoke it, and the side-effect guarantee. Nothing is repeated and the highest-value clause (account email plus counts) is front-loaded.

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 no parameters, so the description carries the burden, and it does: it names what comes back (email, note count, project count) and its chat-scoped nature. For a trivial zero-argument diagnostic tool this is complete enough to call correctly on the first try.

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 correctly implies no input is needed and frames the call as a pure diagnostic read, which matches the empty schema with additionalProperties=false.

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?

"Dice con qué cuenta (email) está conectado MemoryBrain en este chat y cuántas notas y proyectos tiene" states a specific verb (report) plus concrete return content (account email, note count, project count) scoped to the current chat. It is clearly not a list/search tool, though it does not explicitly distinguish itself from the overlapping 'comprobar que la conexión funciona' use case that brain_health likely covers.

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?

Four concrete trigger situations are given: user asks which account is active, user cannot see their notes, user suspects a different email was used, or a connectivity check is needed. That is strong when-to-use guidance, but there is no explicit exclusion or named alternative for the connectivity-check case where brain_health may be the better sibling.

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