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

Annotations already cover readOnly/idempotent/non-destructive, and the description goes well beyond them by disclosing the computation methodology: entry prices derive from the wallet's buy transfer history, tokens without a payment are excluded from the average, unknown block ETH prices fall back to the current price and mark the result approximate, gas is ignored, sale proceeds only count when routed via LI.FI or OKX, and token-to-token swaps have no entry price. These caveats directly affect how an agent should present the numbers and are exactly the context annotations cannot carry.

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?

Purpose and read-only framing are front-loaded, followed by the methodology caveats in a single dense paragraph. Every clause carries information about how the figures are derived or where they are unreliable, though the run-on list of exclusions could be broken up for faster scanning.

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 takes on the burden of describing return values, and it does so by enumerating per-token and total unrealized P&L plus average entry price. It also flags the 'approximate' marker so the agent knows to qualify results. Minor gaps remain: it does not say what is returned for a wallet with no qualifying buys or how an unknown ticker is handled.

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 100% — both the ticker parameter ('One stock token, like NVDA. Empty returns every holding.') and the wallet parameter are documented in the schema with an example and default. The description adds no parameter-level detail (e.g., accepted ticker casing or address format) beyond what the schema already provides, so the baseline 3 applies.

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 opens with a specific verb+resource+scope: 'Profit and loss for the stock tokens a wallet holds on Robinhood Chain,' and names the returned values (average entry price, unrealized P&L per token and total). It is clear what the tool computes, though it never distinguishes itself from siblings like stock_portfolio or portfolio_brief, which an agent would have to disambiguate on its own.

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 by the purpose ('read only, no key needed' signals a safe read), but there is no explicit when-to-use vs when-to-use-another guidance and no sibling tool is named as an alternative. An agent can infer that this is the cost-basis view versus a holdings view, but must guess.

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