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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered; the description adds meaningfully more by disclosing two data-source gates: manualPortfolios always present, brokerage accounts only "when they've let AI use it," and that brokers are aggregated. It does not address volume/truncation behavior at the default limit of 100 or what an empty portfolio looks like, which are the remaining behavioral gaps.

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 the resource definition, then the returned data, then the routing rule to market_query — a sensible order. The parenthetical field inventory is long but each item is substantive information about the payload, not filler; a slight trim of the market-data list would lose nothing critical.

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?

There is no output schema, yet the description carries that burden well by enumerating the returned fields (values, cash, margin, weight, cost basis, unrealized P&L, sector, P/E, forward P/E, dividend yield, next earnings, RSI, IV rank). Combined with the gating conditions and the sibling routing rule, an agent has everything needed to decide and call correctly.

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?

Only one optional parameter and the schema already documents it fully, including the default and the "largest first" ordering, at 100% coverage. The description adds no semantics beyond that, so the baseline 3 applies; it neither clarifies nor obscures the limit parameter.

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 resource with a clear scope qualifier ("The user's portfolios (read-only)") and then enumerates exactly what it returns: aggregated broker account values, cash, margin, and per-holding weight, market value, cost basis, P&L, plus market-data fields. The sibling distinction against market_query is made explicit, so an agent can separate the two without opening either 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?

Gives a positive routing rule ("Use for any question about what they own") and a negative one with a named alternative and concrete examples ("my holdings with P/E over 30", "dividend income from my stocks" → market_query). Both when-to-use and when-not-to-use are stated, which is rare.

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