创建 PDS LED Blink 工程

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

With no annotations provided, the description carries the full disclosure burden. It usefully discloses the side-effect scope (generates RTL/FDC/.pds) and, importantly, that the tool refuses to guess device parameters ('工具不内置默认', '工具不替你猜'). However, it does not disclose overwrite behavior for an existing project directory (only hinted at by the force parameter) or whether the tool invokes PDS tooling beyond file generation.

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?

Two dense sentences with zero filler: the first front-loads the action and deliverables, the second delivers the critical invocation constraint. Every clause earns its place, and the most decision-relevant fact (no built-in device defaults) is placed prominently.

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 schema's deep 100% parameter coverage (directory creation, force deletion, timing implications) compensates for most parametric gaps, and the description covers purpose plus the key no-defaults constraint. But with no output schema and no annotations, the agent is left uncertain about the success return value, whether the PDS flow is actually executed, and error behavior when required device info is absent — notable gaps for a 14-parameter mutation 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 description coverage is 100%, so the schema already documents all 14 parameters with rich detail (e.g., clkFreqMhz's effect on create_clock and timing.met, projectDir's auto-create behavior, package mismatch leading to build failure). The description adds only the meta-rule that the four device parameters must be supplied as a complete set from user/Target Profile, which marginally reinforces but does not go beyond the schema text.

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: '创建面向真实板卡的 LED blink PDS 工程' and enumerates the concrete deliverables (RTL、FDC 和 .pds). The '真实板卡' (real board) qualifier plus the LED-blink scope clearly differentiate it from the generic sibling fpga_pds_create_project, while the device-agnostic note ('工具不内置默认') sets it apart from flows that assume device defaults.

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 implies the usage context — it is for real-board LED blink project creation and explicitly preconditions that complete family/device/speedgrade/package must come from the user or Target Profile. However, it never names alternatives or states when-not-to-use; with ~45 siblings including fpga_pds_create_project, the agent must infer the boundary between generic project creation and blink-specific creation rather than being told.

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