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

The annotations already declare this is a write (readOnlyHint=false) that is idempotent and non-destructive, so the safety profile is covered structurally. The description still adds real behavioral detail beyond that: what is modified (redundant entries archived, recurring patterns promoted), what is explicitly safe from change (latest episodes), and that statistics come back. It stops short of saying whether archiving is reversible or how much is removed per run, keeping it below a 5.

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, zero filler: the first gives the operation, mechanism, preservation rule, and return; the second gives use case and sibling routing. The most decision-relevant information (what it does) is front-loaded before the alternative.

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 only two well-documented optional parameters, no nested objects, and annotations covering mutation and idempotency, the definition supplies everything needed to call it correctly. The one residual gap is what happens to individual archived entries over time (recoverability), which the description does not address, though no output schema exists to cover it either.

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 both parameters are already fully documented in the schema, and the description's 'latest episodes' framing largely restates what keep_recent already says ('kept verbatim without compaction'). The phrase 'older episodic history' loosely implies the scope dimension but adds no syntax, default, or edge-case meaning. With the schema doing the heavy lifting, a baseline 3 is appropriate.

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 names a specific verb and resource ('compact older episodic history') and then spells out the mechanism: archiving redundant entries, promoting recurring patterns, preserving the latest episodes. It also states the return ('compaction statistics') and explicitly contrasts itself with the sibling oxyo_sleep_abstract, so an agent can distinguish the two without opening either 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?

It gives a positive use case ('fast episodic cleanup') and names the concrete condition that should route the agent to the alternative instead ('when also distilling code traces into skills'). That is an explicit when-to-use plus a selection rule for the one realistic competitor, not an implied one.

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