sleep

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

With no annotations supplied, the description carries the full burden and does so thoroughly: it describes idempotence, deferred/ripe-dependent behavior, cluster consolidation with preference-flip handling, budget pruning/re-affirmation, performance cost (under a minute at 60,000 records), and the fact that it never edits raw text.

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 dense but well structured: it front-loads the core action and idle-time trigger, then layers in conditional behavior, performance cost, idempotence, and limitations. Every sentence provides operational value for deciding whether to call the tool.

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 complex background maintenance tool with no output schema, the description covers purpose, timing, side effects, idempotence, and performance. The main gap is that `cluster_threshold` receives no semantic explanation, which is notable given 0% schema description coverage.

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 coverage is 0%, so the description must compensate. It explains `keep` as triggering pruning/re-affirmation of the memory budget only when provided or when capacity is configured, but it never mentions `cluster_threshold`, leaving the parameter’s default of 15 and effect unexplained.

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 states a specific maintenance operation: an idempotent sleep-time compute pass that consolidates ripe near-duplicate clusters and prunes/re-affirms the memory budget. It distinguishes itself from recall/remember by being the recommended place for heavy cleanup so those tools stay fast, and it clarifies what it does not do (never edits raw text).

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 explicit timing guidance: call whenever the agent is idle, preferably on a long idle rather than every tick, and notes that a second immediate call does no new work. It also explains the conditional effect of `keep` and positions this as the recommended heavy-cleanup path, making the when/when-not conditions clear.

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