创建最小 PDS 工程

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

No annotations are provided, so the description carries the burden. It discloses that the tool does not guess device/family/package/speedgrade, that board provides pins and generates FDC, and that force deletes/recreates directories. It doesn't explicitly mention side effects beyond force, but the key behavioral traits (no guessing, error behavior, FDC generation) are transparent.

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 compact and information-dense, with the core purpose front-loaded. The parenthetical about board recommendation is slightly dense but earns its place by conveying the key usage decision. No wasted words, but the structure could be slightly cleaner with explicit separation of the two invocation modes.

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 10-parameter tool with no output schema, the description covers the essential decision logic (board vs explicit fields), the error behavior, and the force semantics. It doesn't describe the generated project structure or what the return value looks like, but given the complexity and the rich schema, this is adequately complete for an agent to invoke correctly.

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 the schema already documents all parameters. The description adds meaningful semantics: it explains the relationship between board and the four device fields, clarifies that pinNames is a subset of the design's actual top ports, and specifies that physical loc/freq/iostd all come from the profile. This is value beyond the schema.

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 creates a minimal .pds project for pds_shell compilation, names the specific resources (RTL/constraints/.pds), and explicitly contrasts it with board-physical information. It distinguishes itself from siblings like fpga_pds_create_blink_project by emphasizing 'minimal' project creation and the board/profile mechanism.

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 recommends passing board:<name> and explains the alternative of providing all four fields, including what happens if fields are missing ('缺则报错点名所缺'). It also references fpga_env for listing configured boards, giving clear when-to-use vs alternative guidance.

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