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

Goes well beyond the annotations by disclosing the post-condition: the memory continues to be returned by retrieval with the reason attached, i.e. this is a soft invalidate rather than a removal. It also documents the 404 failure mode and the two error codes, which no structured field provides. Minor tension with destructiveHint=true, but the description's 'no longer valid' framing is consistent with an invalidating write, not a contradiction.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?

Front-loads purpose and the key when-to-use rule in the first two sentences, then the failure mode, then parameters. The 'Args:' docstring block is a bit mechanical and there is a typo ('superseded_por') in a field name an agent may rely on.

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 no output schema, the description carries the return behavior and does so (retrieval still surfaces the memory with the reason). Error codes and per-parameter intent are covered; it could say more about whether supersession is reversible or how it interacts with relations/retrieval ranking.

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 0%, and the description fully compensates: it names all four parameters, gives the enum values and default for viejo_tipo, marks nuevo_id as optional with its type auto-detected, and adds real guidance for motivo (world change vs. correction). This is meaning the schema alone cannot convey.

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States a specific verb and resource ('mark a stored episode or fact as no longer valid') and immediately disambiguates from deletion ('without deleting it'). An agent can tell this apart from delete_procedure or resolve_contradiction without reading further.

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?

'Use it when a stored memory turns out to be false or outdated, not merely old' gives an explicit inclusion criterion plus an exclusion ('not merely old'). The contrast with deletion and the 404 error path further constrain when this is the right call.

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