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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description is consistent with all of them. Beyond that it adds real context: no placement occurs without owner approval, follow-up turns are answered from the same measured rows in about a second, no key is needed, and results are past measurement rather than a promise. That is meaningful added value over the structured hints.

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 core content is packed into a single ~120-word run-on sentence stitched together with em dashes and nested parentheticals, making it hard to scan. The information is mostly relevant, but the structure undermines it — the negotiation rule and the 'nothing is placed' caveat deserve their own short sentences rather than being buried mid-clause.

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 ten parameters and no output schema, the description carries the burden of explaining the return payload, and it does: risk tier, net probable return and lower bound, measured share of starts reaching target, typical days, worst measured move, size, and an ordered `execution` call list. Combined with the annotation coverage of the safety profile, an agent has enough to call this correctly; only sibling routing is absent.

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 schema already documents every one of the ten parameters, which sets the baseline at 3. The description does add some semantics for `reply` and `conversation_id` by showing concrete negotiation phrases and the multi-turn pattern, but the remaining parameters (exclude, symbols, target_pct, usdc_amount, horizon_days) are covered only by 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 verb and resource: it proposes ONE measured trade setup for the owner's goal, chosen as the best row inside their risk tier from ranked setups, plus a lower-risk and a faster alternative. That is far more specific than the title alone and lets an agent distinguish it from measurement or listing siblings. It stops short of naming which sibling to use instead (e.g. theme_journey_propose_fund or find_trade_path), so it earns a 4 rather than a 5.

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?

It explains the negotiation loop concretely: send the owner's words as `reply` with the same conversation_id, with worked examples ('lower risk', 'faster', 'only crypto', 'swap NVDA'). It also states the decision boundary clearly — 'Nothing is placed here; the owner says yes first.' What is missing is any explicit exclusion or pointer to a sibling tool for adjacent jobs.

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