memory_history

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

Annotations provide no hints, so the description carries the burden. It discloses that compaction thins chains past ~30 days and that as_of filters versions by time, which is useful behavioral context. It does not mention side effects (likely read-only) or output size limits, but the mention of compaction and merged events adds transparency beyond the bare schema.

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 moderately sized and well-structured: it leads with the mode distinction, follows with the as_of behavior, and ends with the return shape. The backtick formatting around parameter names aids scanning. It could be slightly tighter by dropping redundant clarifications like 'oldest→newest' appearing in both modes, but it stays within reasonable length.

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?

The output schema is present, and the description specifies the return object shapes for both modes ({entity, attribute, count, versions} and {found, entity, count, events}), so return values are covered. Given the tool's moderate complexity (paging/time filtering, conditional mode), the description covers the essentials: mode selection, chronological order, as_of semantics, and compaction behavior. Missing details like what 'versions' contains or how errors surface are minor for an agent to discover from the output schema.

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 must compensate. It explains attribute (canonical fact slot) and as_of (ISO or epoch, filters versions written by then), but entity is not described beyond the schema typing. The description adds meaning for two of three parameters, which is helpful but not complete for a zero-coverage 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 clearly distinguishes two modes (with and without attribute) and states exactly what each returns: the change history of a fact slot with version details such as writer/session, tx/valid time, and age, or the entity's causal chain of dated events. The verb 'change history' and 'causal chain' are specific and differentiate this from siblings like memory_get or memory_recall.

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 explains when to use each mode: use with attribute to see versions of a specific fact, without attribute to see the chain of events leading to a state. It does not explicitly name alternatives or say when not to use this tool, but the mode distinction is clear enough for an agent to infer the right context.

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