Mnemostack Invalidate

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

With no annotations, the description carries the full burden and does so: it states payloads are mutated in place (invalidated_at, optionally valid_until) with no deletion and no re-embedding, that records leave default recall but remain reachable via include_invalidated/as_of, that missing points are silently skipped, and that index_root guards against cross-root staleness. This is a rich, accurate disclosure of a mutation's side effects and edge cases.

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-loaded with a one-line purpose followed by tightly packed behavioral detail; almost every clause carries information. The closing 'Returns ok, requested, and invalidated' sentence is redundant given an output schema exists, and the parenthetical about a non-sibling tool adds marginal value.

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 4-parameter write tool with no annotations and an output schema, the description covers the mutation semantics, safety profile, edge cases, and scoping guard that an agent needs before calling. Nothing material is left to the annotations, which are absent.

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 the schema already documents ids, index_root, valid_until, and invalidated_at precisely. The description reinforces the intent of index_root ('avoid marking another root's chunks stale') and the valid_until/invalidated_at split, but adds no syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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 opening line gives a specific verb and resource ('Mark memories stale by id') plus the crucial qualifier 'non-destructively', which immediately separates it from any hard-delete behavior. It also positions itself as a write tool alongside mnemostack_graph_add_triple, so an agent knows the operation class 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?

Usage is implied rather than stated: calling out that invalidated facts 'drop out of default recall but stay reachable via include_invalidated / as_of' tells the agent this is the soft-retirement path, and the multi-root note tells it when to pass index_root. However, there is no explicit routing against the listed siblings (remember, feedback, resolve), so the agent must infer when invalidation beats those alternatives.

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