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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the returns are signed URLs (implying temporary/expiring links) rather than raw files, and the payload also contains summary metrics and strategy IDs. It stops short of stating URL expiry, any auth requirement, or what happens when a requested artifact is unavailable.

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?

A single front-loaded sentence that packs purpose and return content with no filler or repetition. It is dense but readable, though the parenthetical list mixes input-controllable artifacts with always-returned extras (summary metrics, strategy IDs) without distinguishing them.

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?

The tool is a read-only getter with five parameters at 0% schema coverage and no output schema, so the description must do more work than it does. It adequately frames the return payload (URLs plus metrics and strategy IDs), but leaves the boolean include* flags and their defaults undocumented. For a simple retrieval tool with annotations covering safety, this is adequate but with a clear parameter gap.

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 0% for all five parameters, so the description carries the full burden. It only incidentally hints at four of the boolean toggles by naming the artifact types (tearsheet, trades, indicators, stats), but never states that these are opt-in flags with default=true, never explains that they control inclusion in the response, and never describes backtestId's role or format. The compensation is partial and indirect.

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 uses a specific verb ('Returns') and a well-scoped resource: signed URLs for visual backtest artifacts, enumerated as tearsheet, trades, indicators and stats, plus summary metrics and strategy IDs. An agent can tell this is a visualization/artifact retrieval tool rather than a data-series tool. However, it never differentiates itself from near-identical siblings such as get_strategy_visuals, get_backtest_artifact or get_backtest_chart_series, leaving the boundary to inference.

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?

There is no when-to-use guidance at all: no statement of prerequisites (e.g. that a backtest must have completed), no indication of when to prefer this over get_backtest_chart_series or show_backtest_dashboard, and no exclusions. The only implicit cue is the phrase 'visual artifacts', which an agent must interpret on its own.

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