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

With no annotations provided, the description carries the burden of behavioral disclosure. It does convey that the tool returns a report (read-only behavior) and lists the types of evidence included, which is useful. However, it doesn't disclose whether the report is generated on-the-fly or retrieved from storage, whether it requires prior evaluation data, or what happens if no evidence exists for the strategy.

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, compact line that front-loads the core concept ('Evidence dossier') and then lists the specific content areas. Every word earns its place; there is no fluff or repetition of the tool name.

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 has an output schema, so return values are documented elsewhere. The description covers the main content areas of the report, which is helpful. However, with no annotations and a single parameter, the description could have added more context about when this report is available (e.g., after an experiment) or how it relates to the strategy lifecycle. It's adequate but not rich.

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%, so the description must compensate for the single parameter strategy_id. The description mentions 'strategy' implicitly via the tool name and the report content, but it doesn't explicitly state that strategy_id identifies which strategy's report to retrieve. The parameter name is self-explanatory, but the description adds minimal semantic value beyond the schema.

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 'Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval' clearly indicates this tool retrieves a report containing evidence metrics for a strategy. It uses a specific noun ('dossier') and lists concrete content areas, distinguishing it from siblings like get_strategy (which likely returns the strategy itself) and get_experiment. However, it doesn't explicitly state the verb 'get' or 'retrieve', though the tool name supplies that.

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 implies usage when one needs evidence metrics for a strategy, and the content list (baseline vs assisted, distribution, CI, failures, last eval) suggests when this report is relevant. However, it doesn't explicitly state when to use this over get_strategy or get_experiment, nor does it mention any prerequisites like requiring a completed experiment or existing strategy.

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