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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. Beyond that the description discloses the shape of the return (structured card with data range, in/out-of-sample split, max drawdown, missing-data flags, plus itemized reasons) and marks the call as free — useful, non-obvious behavior for a diagnostic tool. It still says nothing about latency, limits on how far back a run can be explained, or what happens when the referenced run does not exist, so it adds context but not a full behavioral picture.

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 purpose and the two diagnostic questions come first, then the return contents, then the parameter rule, then the cost note — a sensible front-loaded order with no repetition. The bracketed 【行情】 tag is mild noise and the sentence is dense with parenthetical lists, but every clause carries information.

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?

For a read-only diagnostic tool with three optional params and no output schema, the description covers what the agent needs: what it answers, what comes back, how to parameterize it, and that it is free. The only gap is the absence of any fallback guidance for an invalid or unknown runId/jobId/strategyId, which is a modest omission given the tool's simplicity.

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%, so the baseline is 3, but the description adds a constraint the schema does not encode: all three identifiers are optional in the schema and the 'at least one, pick any one' rule is only stated in prose. That is genuine value beyond the structured fields, particularly the 'three-choice-one' disambiguation an agent would otherwise have no way to infer.

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 states a specific verb and resource — explain a single backtest — and sharpens it with the two concrete questions it answers ('why it lost money / why no fill happened'). That is far more informative than the title alone. It does not name the neighbouring tools it might be confused with (platform_backtest_result, platform_run_backtest), so sibling differentiation is only implied through the 'explain/why' framing.

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?

Clear triggering context is given (diagnose losses or missing fills after a backtest) and the invocation rule 'at least one of runId / jobId / strategyId, any one is enough' is stated explicitly. It stops short of saying when to prefer this over platform_backtest_result or platform_run_backtest, so it is clear context without alternatives.

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