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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds meaningful behavioral details beyond these: dividends are excluded from returns, split ratios are handled with a fallback to exclude earlier closes when unusable, and the valuation uses raw closing prices. These are non-obvious behaviors that materially affect results and are not inferable from the schema or annotations.

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 a single verbose paragraph, but every sentence earns its place—purpose, mode selection, reconstruction/rebalancing details, return metrics, and split handling are all packed in. It is front-loaded with the core purpose. While it could be broken into bullet points for readability, it is not bloated and remains efficient for its complexity.

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?

Given the tool's complexity (backtest logic, snapshot reconstruction, split handling) and the absence of an output schema, the description does a thorough job. It specifies the exact return metrics (price return, CAGR, max drawdown, alpha), explains the date range logic, institution resolution, and benchmark default. An agent has enough information to invoke the tool correctly without ambiguity about inputs or expected outputs.

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 every parameter has a description. The tool description adds value by clarifying interactions: fromDate overrides windowYears, windowYears is clamped to 1-20, and institution accepts names/CIKs with resolution behavior (unique partials, aliases, ambiguous partials return candidates). This enriches the schema descriptions without being redundant.

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 starts with the specific verb 'Backtest' and a precise object: how cloning an institutional filer's reported 13F portfolio would perform against a market benchmark. It clearly distinguishes this from the many other institution-related tools (e.g., GetInstitutionPortfolio, GetInstitutionQuarterlyActivity) by focusing on backtest performance, not holdings or activity. The first sentence alone fully defines the tool's purpose.

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 explicitly explains the two modes of operation (trailing window via windowYears, or explicit fromDate/toDate range) and notes that fromDate overrides windowYears when both are supplied. It also mentions the rebalancing on the SEC filing lag, giving context for how results are produced. However, it does not explicitly contrast with alternative tools (e.g., 'use this instead of X when...'), though given the unique purpose, this is a minor omission.

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