aya_memoria_grafo_observar

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

Annotations already declare this is non-read-only, non-destructive, and idempotent. The description adds modest context by noting observations are 'atomicas' and by requiring an existing entity, which hints at failure cases and data-shape expectations, but it doesn't explain duplicate handling, return behavior, or side effects beyond adding observations.

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?

The description is a single, front-loaded, information-dense sentence with no filler or repetition. Every word contributes meaning, making it easy for an agent to parse quickly.

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 simple two-parameter mutation with useful annotations, the description is minimally adequate. Gaps remain: it doesn't state what happens when the entity is missing, whether duplicate observations are ignored, or what the tool returns, and no output schema is provided to fill those gaps.

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 0%, so the description should compensate for unclear parameters. It vaguely maps 'id' to an existing entity and 'observacoes' to atomic observations, but it doesn't explain id format, observation content guidelines, or relationship to other graph operations.

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 uses a specific verb ('Acrescenta') and a clear resource ('observacoes atomicas a uma entidade existente'), so an agent can tell it adds atomic observations to an existing graph entity. It doesn't explicitly contrast with siblings like upsert, relacionar, or remover, but the intended action is still distinct and understandable.

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?

The phrase 'a uma entidade existente' implies a prerequisite: the target entity must already exist, so this tool is for enriching existing entities rather than creating them. However, it doesn't explicitly say when to prefer this over sibling operations like upsert or relacionar, leaving usage routing mostly implicit.

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