learn_report

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it largely fails. It does not say whether the report is computed on demand, whether the write parameter persists state (a potential mutation), whether ablation triggers expensive recomputation, or anything about auth/permissions. Only the topic list hints at what is produced.

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?

It is a single compact line with no wasted words, but it is a noun phrase fragment rather than a front-loaded sentence with a verb, so it reads more like a section list than an actionable description. Adequately sized but structurally weak.

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 no annotations, no output schema, and 0% parameter coverage, the description is the only source of information and it omits the write/ablation semantics and any indication of return shape. For a tool with side-effect-implying flags, this is insufficient.

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 both parameters. The description's mention of 变体消融 (variant ablation) loosely maps to the ablation flag, but the write flag is completely undocumented in both schema and description, leaving half the parameter surface unexplained.

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 names the resource (学习算法报告 / learning algorithm report) and enumerates the report's contents — ability/difficulty, calibration, pattern risk, teaching-method ranking, variant ablation — which is more than a tautology. However it lacks a verb (generate? return? compute?) and never distinguishes itself from siblings like learn_predict, so an agent must infer that this is the aggregate reporting endpoint.

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 statement of when to use this tool versus the many siblings (learn_predict, review_due, review_grade, etc.), nor any prerequisite or trigger condition. The agent is left to guess that this is the summary/report view after other learning steps.

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