memory_history

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

Annotations already declare readOnly and closed-world behavior; the description adds real behavioral context by disclosing tombstone inclusion and that historical values may conflict. It still omits return shape and ordering, but the data-quality caveats are valuable beyond the annotations.

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?

Two compact sentences, with the core purpose first and the caveat second. No filler; every clause adds scoping or warning information.

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 tool is simple and annotated read-only, and the description gives enough to understand the audit purpose and caveats. But with no output schema and no parameter descriptions, the agent still lacks return shape and precise input semantics, so it is only partially complete.

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 explain both parameters. 'Known by cutoff' loosely maps to as_of, but memory_id is never described and no cutoff/date format or semantics are given.

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 identifies a specific resource—audit revisions of a memory—and scope—known by a cutoff, including tombstones. It does not explicitly name memory_search or memory_status or use a direct retrieve/list verb, so sibling differentiation is only implicit.

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?

It signals an audit/historical use case and explicitly warns 'this is not answer context,' which is a useful when-not cue. However, it never names the sibling tools to use for answer context or states exactly when audit history is required over memory_search, leaving alternatives implied.

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