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

The description goes well beyond the minimal annotations (readOnlyHint=false, destructiveHint=false) by disclosing the draft-only lifecycle: saved to user's account, appears under 'Pending AI drafts', user must explicitly accept or discard, and never changes live positions. It also explains the unresolved-ticker behavior (returned in `unresolved` and skipped), adding valuable context.

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 description is long but every sentence earns its place: usage context, sibling distinction, gating, draft lifecycle, universe constraints, and alternative tool. It is front-loaded with 'Use when...' and contains no fluff or repetition.

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?

Despite no output schema, the description covers the essential lifecycle (draft saved, user review, accept/discard), unresolvable ticker handling, and prerequisites. It doesn't explicitly describe the success response structure (e.g., draft ID), but given the tool's moderate complexity and the detail provided, it is nearly complete.

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 baseline is 3. The description adds extra meaning by explaining weight versus amount mode, cash handling (remainder held as cash, normalisation), and cashPct overriding the weight-remainder rule. This goes beyond the schema's per-parameter descriptions, though not dramatically.

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 ('persists') and resource ('a REVIEWABLE paper-portfolio draft') with clear scope: exact tickers supplied by the user, sized by weight or USD amount. It explicitly contrasts with create_portfolio_draft by stating it does NOT use the LLM and never re-selects tickers, making sibling differentiation strong.

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 gives explicit when-to-use ('when YOU have ALREADY decided the exact holdings') and when-not-to-use ('For a vague brief where the model should pick, use create_portfolio_draft instead'). It also clarifies gating (not Pro-gated), required OAuth scope, and the need to confirm tickers in Bullrun's universe.

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