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

The description explicitly states the tool performs mutations ('upsert up to 100 texts', 'per query or delete'), while annotations declare readOnlyHint=true. A write/delete tool declared read-only is a direct contradiction that could lead an agent to think this is a safe side-effect-free read. The otherwise useful context (wallet-keyed privacy, server-side multilingual embedding, pay-per-call via x402) cannot overcome the conflict.

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?

Purpose is front-loaded in the first clause and the description stays to three sentences. The two cost sentences partially overlap ('from $0.004 per upsert batch (by size), $0.003 per query or delete' vs '$0.012 USDC per call'), which adds slight noise without adding information.

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 multi-action tool with no output schema and one required parameter among five, the description covers cost, embedding behavior, and 100-item limits well but never says what query returns (matches/scores/ids?) or what upsert/delete return, and gives no guidance on the read-only conflict. Adequate but with visible gaps.

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 60% and the description meaningfully supplements it: it states text is up to 100 items with metadata, that embedding is performed by the service and is multilingual (so callers must not pre-embed), and that billing varies by upsert batch size, query, and delete. top_k and the id field's format are left to the schema, which is acceptable.

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?

Names a specific resource and mode set: private long-term vector memory with upsert, semantic search, and delete. The 'Keyed to the paying wallet' scope and 'we embed them, multilingual' clause make it concrete. It never names or differentiates itself from near siblings such as memory, kb, embed, or embeddings, so an agent must infer which of those applies.

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 'upsert ... then search by meaning' phrasing implies the workflow and the schema notes query is the default action, and pricing hints at the three operations. There is no explicit when-to-use guidance and no exclusions against the very similar memory/kb/storage siblings, so selection still requires inference.

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