aya_memoria_grafo_upsert

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

Annotations already signal readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the description correctly aligns with an upsert write operation. The description adds useful behavioral context beyond the annotations by mentioning 'observacoes atomicas' and 'sanitizacao de segredos', which indicates how observations are handled. No contradiction with the annotations is present.

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 one concise, front-loaded sentence with no filler words. It communicates the action and two important behavioral characteristics efficiently. It is slightly too terse to fully support correct invocation, but as a description it is well-sized.

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?

Given no parameter descriptions, no output schema, and many sibling memory-graph tools, this single sentence is not enough for reliable invocation. It does not explain what id and tipo should be, how the graph entity is interpreted, or how it differs from adjacent tools like grafo_observar, grafo_relacionar, or memoria_atualizar_estado. The annotations cover safety and idempotency, but not selection or invocation details.

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 carries the full burden for explaining parameters. It adds only partial meaning for 'observacoes' via the phrases 'observacoes atomicas' and 'sanitizacao de segredos', but id and tipo are completely unexplained despite being required. An agent cannot determine what values id or tipo should take from the description or schema.

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 states a specific action ('Cria/atualiza') and a clear resource ('entidade de memoria'), so an agent can tell this is an upsert operation. It adds meaningful qualifiers about atomic observations and secret sanitization, which helps separate it from read/query siblings like aya_memoria_grafo_ler or buscar. It does not explicitly name a sibling alternative, but the core purpose is clear and non-tautological.

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 description implies when to use the tool: when creating or updating a memory entity with observations. However, it gives no explicit guidance about when NOT to use it or which sibling memory-graph tools should be preferred for related operations. With many sibling tools such as grafo_observar, grafo_relacionar, and grafo_remover, clearer routing would have been valuable.

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