sw_throughput

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

No annotations were provided, so the description carries the full burden. It discloses that BLER is a model, not a measurement, and explicitly lists the three real-world losses (modulation limitation, code rate granularity, finite block length + implementation loss). It also reveals the behavioral nuance that MCS saturation indicates a table limitation rather than channel limitation. This is far more than typical disclosure.

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 lengthy but well-structured: it opens with a clear definition, uses a numbered list for the three losses, and separates output metrics from MCS table guidance. Every sentence earns its place, and the formatting aids readability. It is slightly longer than strictly necessary but appropriate for the tool's complexity.

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 description provides rich context about methodology, output metrics, and limitations, and an output schema exists. However, with 5 parameters and zero schema descriptions, key parameters like `method`, `max_samples`, and `target_bler` are left unexplained. This gap means an agent may not know how to set them correctly, making the tool only partially complete for correct invocation.

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 explains `mcs_table` thoroughly (1 vs 2, 38.214 tables), but says nothing about `method`, `max_samples`, or `target_bler`. These parameters remain ambiguous, and the description does not provide enough detail for an agent to select appropriate values. While `dataset_id` is self-evident, the others need explanation.

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 opens with a specific verb+resource: '算**真实吞吐**（Mbps）与 3GPP 口径的边缘用户指标' (compute real throughput and 3GPP edge user metrics), and explicitly contrasts with the sibling `sw_link_performance`, which computes the Shannon-bound spectral efficiency. This clearly differentiates the tool's purpose from alternatives.

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 explicitly explains when to use this tool vs. `sw_link_performance`: the latter provides only an unattainable Shannon upper bound, while this tool models real-world losses. It also gives concrete guidance on MCS table selection (if MCS distribution saturates, switch to table 2) and cautions that strict BLER conclusions require a link-level simulator. This directly answers 'when to use' and 'when not to use'.

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