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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered. The description adds real behavioral context beyond them: empty-state handling ('If none connected, send them to https://gogi.ai/voice-agent'), a guard against fabrication ('Do not invent account IDs'), and the display contract for results. A minor gap is that it doesn't address caching or refresh behavior, but this is well above the annotation baseline.

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?

Front-loaded with purpose and scope before the sequencing instruction, and every clause carries a distinct directive (ordering, display, follow-up question, preference, fallback, anti-hallucination). It is dense and long for a zero-parameter read, with some instructional overlap, but nothing is pure filler.

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?

No parameters, full schema coverage, annotations present, and an output schema exists — so return values need not be explained. Within that context the description is more than sufficient, covering scope, ordering, presentation, and the empty case.

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?

The tool takes zero parameters, so the baseline is 4. The description does explain a related machine field (the integer `id` used as broker_account_id elsewhere) and warns against verbalizing it as a 'Gogi ID', which is useful cross-tool semantics even though it isn't a parameter of this call.

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 ('List ALL connected broker accounts and wallets') and immediately narrows scope with '(Alpaca, TradeLocker, Kalshi, Coinbase, etc. — never Alpaca-only)', which distinguishes it from any broker-specific sibling. An agent can tell what this returns without opening the schema.

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?

Explicitly names the prerequisite sequence: 'Call BEFORE create_instance / create_and_start_algo / execute_trade / close_positions.' It also states the downstream step (ask the user which account, then pass that account's id as broker_account_id), so both when-to-call and what-to-do-next are covered. Exclusions are implicit in the ordering constraint but the guidance is unusually complete.

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