memory_search

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

With no annotations, the description carries the full burden and does so well: it discloses metering, the exact 402 http_status behavior, the x402 v2 payload location, the price and network (0.001 USDC on Base), and the non-obvious retry semantic that a 402 does not consume the nonce. That is precisely the behavioral context an agent cannot infer from 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?

Two tight sentences, purpose front-loaded, payment mechanics second. No wasted words while still conveying the retry constraint.

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 12-parameter, 5-required tool with no output schema, the description covers the payment/auth behavior thoroughly. It stops short of describing the prepare-then-search prerequisite chain and the shape of search results (matching, ranking, pagination), which are the remaining 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 description coverage is 100%, so all 12 parameters are documented in the schema itself; the baseline is 3. The description only ties payment_signature to the 402 retry flow, adding marginal meaning beyond that, and explains none of the other parameters.

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 verb and resource: 'Semantic search over YOUR memories only, ranked by real cosine similarity.' The 'YOUR memories only' scoping and cosine-similarity ranking distinguish it from sibling reads like memory_get or memory_history, though it never names them 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 strong guidance on the paid invocation path (free with MEMORY_API_KEY, otherwise pay and retry with the SAME arguments plus payment_signature), but gives no guidance on when to choose this over sibling tools such as memory_get or memory_history, nor that memory_prepare must run first to obtain nonce/timestamp/signature.

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