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

Beyond readOnly/idempotent/non-destructive annotations, it discloses that nothing is stored, rewritten or deleted, no model is called, the output is deterministic, and there is a 32 KiB free limit. It also names exactly what comes back and warns to exclude secrets and personal data — real behavioral value the annotations don't carry.

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?

Front-loads 'START HERE' and the stateless/no-write guarantee, then usage triggers, then what's returned, then limits. Every sentence carries distinct information; no filler despite the density.

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 a single deeply nested parameter, no output schema, and annotations covering safety, the description does the remaining work: it explains the return shape, the statelessness, the free-tier limit, and the data-hygiene caveat. Nothing essential for a correct first call is missing.

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 100% and the bundle schema is heavily self-documented, so the baseline is 3. The description still adds meaning by enumerating what the bundle should contain (memories/facts, tool schemas, plans, logs) and the size cap, though it doesn't mention the schema's 'memories or facts alias, never both' rule or item count limits.

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 action — send a JSON bundle, receive a deterministic keep/archive/drop diff with per-item reasons, a slimmer bundle, and token estimates. That behavior (stateless, nothing stored/rewritten/deleted) implicitly separates it from consolidate/consolidate_apply, but it never names those siblings explicitly.

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?

Gives concrete triggers: context/memory/tool list has grown long, before starting a new task, or hunting duplicates, superseded, expired or cold memories and unused tools. It does not explicitly say when to skip it or point at consolidate_apply as the follow-up, but 'START HERE' plus the no-write guarantee makes the sequencing clear enough.

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