sw_link_performance

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

With no annotations, the description carries the burden. It discloses the return content (mean, 95% CI, convergence judgment) and a critical caveat: '不收敛时方案间的差异可能只是噪声' (when not converged, differences may be noise) and that this is explicitly marked. It also explains the behavior of use_estimated_csi (estimated CSI for precoding, ideal CSI for evaluation). This is substantial behavioral disclosure beyond the schema, though it doesn't cover all edge cases like error handling or prerequisites.

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 well-structured: a one-line summary of the pipeline, a context sentence about its role in Monte Carlo simulation, and a focused parameter section with clear bullet points. Each sentence adds value, and the bold warning about convergence is front-loaded. It is appropriately sized for a tool with 5 parameters and no schema descriptions.

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?

Given the complexity (5 params, no annotations, no schema descriptions), the description covers the essential aspects: what it computes, the key use case, parameter semantics for the main variables, and the output interpretation (convergence, CI). The output schema exists, so detailed return values need not be described. The main gap is the lack of context for dataset_id and snr_db, but overall the description is sufficient for an AI agent to select and invoke the tool correctly in most cases.

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. It does add meaning for three of five parameters: methods (explains each precoding type and defaults), use_estimated_csi (what true does), and receiver (lists mmse/zf/mrc). However, dataset_id (required) and snr_db are not explained. While these may be self-explanatory from their names, the description misses the required parameter and does not fully compensate for the low schema coverage.

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 clearly states the tool's function: '算谱效：预编码 → 逐层 SINR → 频谱效率' (calculate spectrum efficiency via precoding → per-layer SINR → spectral efficiency) and explicitly mentions horizontal comparison of multiple precoding schemes. This is a specific verb+resource+output, distinguishing it from siblings like sw_throughput or sw_sweep_snr by focusing on link-level precoding comparison.

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?

It provides clear context: '这是蒙特卡洛仿真最常用的评价链路' (the most common evaluation link in Monte Carlo simulations), implying when to use it. It also gives guidance on methods, e.g., '用户自研方案应当和这几个在同一批信道上比' (user-defined schemes should be compared on the same channels), and on use_estimated_csi for CSI feedback topics. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of a 5.

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