Inventario acumulado

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

readOnlyHint=true already declares the safety profile, so the explicit "No lanza escaneos" is largely redundant with the annotation. The description does add genuine context beyond annotations: the data is cumulative and grows with each run, and history is keyed by fingerprint. It omits operational traits an agent would want, such as pagination, default view behavior, and whether an empty inventory is a normal state.

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?

Two sentences, front-loaded with the core purpose before the enumeration, and the negative constraint (no scans) placed last where it matters as a filter. The long parenthetical of finding states is dense but every element maps to a real capability. Slightly heavy for a single sentence but no 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 9-parameter, zero-required query tool with no output schema, the description establishes the conceptual model well but leaves the filtering surface (status, category, severity, limit, include_suppressed) and the return shape entirely to the schema. An agent can pick a view but would still need the schema to build a filtered call correctly.

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?

With 56% schema coverage across 9 parameters, the description compensates meaningfully: it names the four view modes in prose, explains the new/persistent/gone lifecycle that underpins the `seen` enum, and clarifies that history is looked up "por su huella" (fingerprint). It says nothing about limit, status, category, severity, or include_suppressed, which remain schema-only.

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 opens with a specific verb and object ("Consulta la memoria larga de Xolotl") and then enumerates the exact contents returned: ecosystem summary, assets seen, findings across time, and per-fingerprint history. The closing line "No lanza escaneos" actively separates it from the many scan_* siblings, so an agent can distinguish it without opening the schema.

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 states a positive use case ("base para explorar sistemas y armar un inventario") and one exclusion (it does not launch scans), which is real guidance. However, it never names an alternative for overlapping needs such as findings_query, finding_get, or runs_diff, so the agent must infer which retrieval sibling to pick. Usage is implied rather than prescribed.

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