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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds genuinely non-redundant context: it is a paid x402 call at 0.003 USD and is restricted to manual-desk use, both of which materially affect invocation. What is missing is staleness/TTL of the cache and any rate-limit detail, which matters for data that is by definition cached.

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?

Three short clauses with the cost front-loaded and no filler. It is efficient, though the terse fragments ("Manual-desk only; not advice") trade a little clarity for brevity.

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 no output schema, the description must convey the shape of the return value, and it does not — an agent paying 0.003 USD cannot tell whether it gets anomaly scores, option chains, or a radar summary. Combined with vague purpose language and unspecified cache freshness, this is a significant gap for a paid, output-less tool.

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?

There is a single parameter and the schema description covers it at 100%, including the key omit-to-receive-payment-requirements behavior, so the schema carries the load. The description adds no additional parameter meaning, which lands at the baseline.

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?

"Cached options radar and anomaly intelligence" identifies the resource domain (options data) and marks it as cached, implicitly differentiating it from the sibling mnemos_options_scan. However, "radar" and "anomaly intelligence" are vague jargon with no concrete verb or statement of what is actually returned, so an agent cannot fully tell what the tool produces.

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?

"Manual-desk only; not advice" gives a caveat/audience restriction but no guidance on when to invoke this versus mnemos_options_scan or mnemos_arb_scan. There is no stated precondition, exclusion, or alternative-routing rule beyond the implied cached-vs-live distinction.

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