CDT 通用 Tcl 直通 (受护栏)

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

With no annotations, the description carries the safety burden and discloses critical behavior: destructive write-device operations are gated by confirm and expectIdcode plus a scan check, and connect:true silently wraps commands in connect/scan_chain/disconnect while raw tcl uses {{PORT}}. It does not spell out exact failure modes or return format, but the guardrail and connection behavior are well covered.

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 dense but optimally sized, front-loading purpose and then adding guardrail and connection rules. The compressed notation (cfg_jtag_flash_erase|program, confirm:true) is efficient, though slightly less readable, so a 4 is appropriate.

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 12-parameter, no-annotation, no-output-schema tool, the description covers guardrails, invocation modes, and coverage, but it omits what the tool returns (raw Tcl output? summary/full structure?) and does not position the tool against the many fpga_* siblings. This leaves an agent with meaningful gaps for a high-complexity tool.

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 baseline is 3, and the description adds real interaction semantics: connect:true pairs with commands, raw tcl requires {{PORT}}, and confirm/expectIdcode are tied to write-device commands. This tells an agent how the parameters relate, which the bare schema does not.

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 runs arbitrary cfg_* (cdt_cfg) or dbg_* (cdt_dbg) Tcl against cdt_js and enumerates the covered operations (scan, read, config, SPI flash, ILA, virtual-IO). It does not name explicit sibling tools for differentiation, so it earns a 4 rather than a 5.

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 gives clear operational conditions: read-class commands are unrestricted; write-device commands require confirm:true and expectIdcode with prior scan validation; connect/scan/disconnect auto-wrapping depends on commands vs raw tcl. However, it never says when to choose this generic pass-through over the many specialized siblings (fpga_jtag_scan, fpga_flash_*, fpga_ila_*), so usage vs alternatives is only implied.

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