guardar_nota

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

With no annotations, the description carries the full burden and does disclose two non-obvious behaviors: entries are indexed and duplicates are not created ('devuelve la cita original' instead). It says nothing about persistence scope, whether saved notes can later be edited or removed, size limits, or any failure mode — gaps that matter for a mutation tool with zero annotation coverage.

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, front-loaded with the action, then the dedup rule, then the trigger condition — no filler. The parenthetical examples of what a memory is do useful disambiguation work rather than padding.

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 two-parameter write tool with no output schema, the definition covers what to save, when to save, and what happens on a duplicate (returning the original citation), which is the key return-value behavior an agent needs. Only mutation limits and reversibility are left implicit.

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 description coverage is 100%, so both 'texto' and 'etiquetas' are already documented in the schema, making 3 the baseline. The dedup sentence does add real meaning about how 'texto' is matched ('si el texto ya existía'), but nothing further is said about tags or how they affect retrieval.

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 specific verb+resource ('Guarda un dato nuevo en la memoria') and immediately scopes it with concrete examples of what counts (una decisión, una preferencia, un dato del usuario), plus the indexing side effect. It does not explicitly name a sibling, but the write-vs-read split against buscar_memoria/leer_fragmento is obvious from 'guarda' and 'deja indexado'.

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?

'Usala cuando el usuario diga algo que convenga recordar en próximas sesiones' gives a clear invocation condition tied to the conversation, which is exactly the trigger an agent needs. It stops short of explicit exclusions (e.g. don't save transient chatter, don't use for lookups) or naming the retrieval sibling to use afterwards.

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