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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral context on its own — polling semantics, a 100-trade page size, and that studies default to the newest 20 runs. It stops short of saying what an errored or expired run_id yields, which keeps it from a 5.

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 compact sentence with the primary mode front-loaded and no wasted clauses. The stacked parentheticals make it denser than ideal to parse, but every clause adds a distinct fact.

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 an output schema present, return values need no explanation, and the description still covers both modes, polling, and trade pagination. Only minor gaps remain, such as distinguishing the before_version paging path that the schema handles alone.

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 80%, so the schema already documents run_id, study_id, trades_page, and before_version. The description mostly restates those pairings ("one of them with version") rather than adding syntax or format detail, so the baseline of 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?

States a specific verb (reads) and resource (a backtest result) and enumerates both access modes: by run_id for a single run, or by study_id for a study's runs. An agent can immediately tell this is the retrieval counterpart to run_backtest/run_held_out_test.

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?

Gives explicit conditional guidance: call this when run_backtest answered "running" and keep polling until the run ends. Also distinguishes the study_id path and its version qualifier. This is genuine when-to-use instruction, not inference.

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