Audit memories

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true; the description adds real value beyond them by naming the exact write target (JEVMEM.md) and the fact that writes only occur with apply=true. It does not explain what happens to memories that remain stale or how re-scoring is performed against the repository snapshot, leaving some behavioral gaps.

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 sentences, front-loaded with the core action and scoped by the parameter behavior in the second. No filler or restatement of the tool name.

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 single-parameter mutation tool with no output schema, the description covers the action, the evaluation intent, the default, and the write target. The one remaining ambiguity is what the caller receives back (a report of flagged memories?) and whether the audit itself mutates stored records.

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?

With only one parameter and 0% schema description coverage, the description carries the burden and does so: it explains that apply=true writes [stale?] flags while the default is a non-persisting pass. The boolean's semantics are therefore clear even though the schema documents nothing.

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 ('Re-score every live memory ... and flag stale ones') plus the evaluation criterion ('is this still true?'). It is clearly distinguishable from siblings list_memory, search_memory, and add_memory, which are retrieval/addition tools rather than a re-scoring pass.

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 gives a concrete decision rule for the one parameter: omit apply for a scoring/flagging pass, set apply=true to persist flags into JEVMEM.md, implying a dry-run default. It does not name alternative tools or state when not to run an audit, so it falls short of full when/when-not guidance.

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