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

Annotations already mark the tool read-only and non-destructive, but the description adds substantial behavioral detail beyond that: signed quantities, owner-cost basis never split-restated, session-marked lots, unknown (never zero) values for unpriceable/expired positions, and the role of returned lot ids in update/close/remove tools. This gives the agent a clear model of how results behave.

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?

Every sentence in the description earns its place: core purpose, parameter usage, data semantics, edge cases, and sibling differentiation. The text is dense but not verbose, and the most critical usage guidance appears near the front.

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 carries the burden of explaining return content Key fields are named (lots, cost basis, profits, watched instruments), and special value semantics are clarified. For a single-optional-parameter read-only tool, this is complete enough for an agent to invoke it and interpret results 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?

Although the schema already documents the portfolio parameter as optional and says to omit it to list portfolios, the description adds the crucial exact-one-returned-in-full behavior and explicitly states that passing a name selects a portfolio. This goes beyond the schema's basic description and gives the agent actionable semantics for the only 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?

The description begins with a specific verb and resource: 'Get the caller's saved personal portfolios,' and enumerates the included data (lots, cost basis, realized/unrealized profit, watched instruments). It also explicitly differentiates itself from GetInstitutionPortfolio by directing 13F holdings queries to that sibling, making the tool's purpose unmistakable.

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?

The description gives precise call guidance: omit portfolio to list portfolios, with the edge case that a single existing portfolio is returned in full, and pass the name to select one. It also names the alternative tool (GetInstitutionPortfolio) and clarifies that watched instruments are not positions, which prevents misuse.

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