El cerebro del conector (memoria del negocio)

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

The description states the tool saves data ('guarda lo que el vendedor le enseña') and deletes it ('olvidar'), while annotations declare readOnlyHint=true. This is a direct contradiction between the described write/delete behavior and the declared read-only nature. The otherwise useful disclosure that data stays in a local file on the seller's machine cannot offset the contradiction.

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?

It is front-loaded with the purpose statement and ends with a compact action list, but the middle section is a dense run-on of dashes and capitalized emphasis that mixes guarantees, SKU rules, and privacy notes. Each sentence carries information, yet the formatting makes it slower to parse than needed.

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 9 parameters, no output schema, and a contradictory annotation, the description should carry more weight. It covers storage scope, SKU behavior, and privacy well, but never says what 'ver' returns, what 'olvidar' removes (one SKU, one product, all notes?) or whether deletion is recoverable.

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 already 100%, so the baseline is 3, but the description adds genuinely new semantics: costs are keyed by SKU and propagate to all listings sharing that SKU, including future ones, and item_id may itself be a SKU (e.g. "TER-1L"). That inheritance rule is not derivable from the schema alone.

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 first sentence defines a specific resource (a local business memory database) with concrete stored fields (costo, % impuestos, envío, medidas, incluye, notas), and the closing 'Acciones: guardar, ver, olvidar' enumerates the operations. It is clearly distinguishable from siblings like ml_rentabilidad, which it explicitly positions as a consumer of this data.

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 tells the agent when to save (costs, taxes, shipping, measurements) and even gives a conditional rule for business-wide data ('para datos del negocio entero... guardar sin item_id'). It stops short of stating when NOT to use the tool or how 'ver'/'olvidar' differ in scope, but the context for use is clear.

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