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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's added value is real and specific: it discloses the data-availability constraint (only brokers that report history) and the retention behavior (Gloom keeps history past the broker's one-year window). It also defines how oneYearReturn is computed, which is behavior the annotations do not cover.

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?

Two tight sentences, front-loaded with the read-only scope and retention fact, then the oneYearReturn semantics. Slightly dense in the compound clause structure, but no wasted words.

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 usefully names the returned series (daily value + returns) and explains the oneYearReturn field's compounding rule and short-series fallback. Gaps remain around date defaults, pagination/range limits, and how accountId interacts with broker, but the core return shape is covered.

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 coverage is 67%, with since and broker documented in-schema but accountId undocumented anywhere. The description echoes the broker/history dimension but adds no syntax, defaults, or meaning for since/accountId beyond what the schema already says, so it only partially compensates for the coverage gap.

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 (daily account value and return series) and scope (only brokers that report history, Interactive Brokers today), which cleanly separates it from sibling time-series/position tools like portfolio.positions and market.history. The 'read-only' framing plus the retention note tells an agent exactly what it will get back.

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?

Usage is implied rather than stated: the mention of brokers that report history and IBKR hints at when the tool returns data, but there is no explicit 'use this when you want X, use Y otherwise' guidance among the many portfolio/market siblings. No preconditions or exclusions are given.

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