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

With no annotations provided, the description carries full responsibility. It discloses the paid nature (0.005 USDC), prompt-injection exclusion, deduplication to most-recent belief, budget-packing behavior, and the ability to assemble as of a past time. These are non-obvious behaviors beyond the schema.

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 front-loaded with the cost warning and packs multiple behavioral details into a compact five-sentence structure. No filler or redundant phrases.

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?

Given the tool has an output schema and the description covers cost, filtering, deduplication, time-travel, and return format, it is sufficiently complete. It also mentions returning an x402 quote, which is a cost-related operational detail. Without annotations, this description compensates effectively.

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 the baseline is 3. The description does not add substantial new meaning beyond what the schema already provides for query, k, as_of, and max_chars. It mentions max_chars in the context of budget-packing and as_of for time-travel, but these are already described in the schema.

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 purpose: 'searches your memories, dedupes to the most-recent belief per key, budget-packs them into max_chars, and returns a ready-to-paste context block plus structured provenance.' This clearly differentiates it from sibling tools like mnemos_search by focusing on pre-completion context assembly with deduplication and budget-packing.

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 opening 'The endpoint to call right before a completion' establishes a clear when-to-use context. It also notes optional 'AS OF a past time,' implying historical assembly. However, it doesn't explicitly name alternative tools or state when not to use it, so it stops short of a 5.

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