Model files and initialization / 模型文件与初始化

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

Annotations already flag destructiveHint=true, but the description goes well beyond them: paths are interpreted by the QiaoTong host (possibly a remote Windows machine) rather than the MCP client, initialize_model requires confirm=true, open can discard unsaved work, save can overwrite, and there is no automatic backup or rollback. It also warns to verify the active model and discloses the return shape (a completion message, not model contents).

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?

Front-loads purpose, then routing, then behavioral caveats in a logical order. It is longer than one operation would justify, but the length is earned by three distinct destructive-ish sub-operations. The closing 'save important work first, verify after' mildly repeats the earlier unsaved-work warning, keeping it just short of a 5.

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 polymorphic, destructive file tool this covers everything an agent needs: operation routing, host path semantics, the confirm gate, overwrite/discard risk, absence of backup, and post-call verification. Returns are summarized and an output schema exists, so no further return-value detail is required.

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 baseline is 3, but the description adds a genuine cross-cutting clarification: request.operation selects the matching branch fields, and file paths are resolved on the host rather than the client's local filesystem. That host-vs-client distinction materially changes how an agent should populate file_path, though the per-field detail still lives in 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?

States specific verbs and a resource ('Open, save or initialize the active bridge project') and enumerates the three operations it multiplexes. It actively distinguishes itself from siblings by naming edit_geometry and manage_checks as the tools for entity edits and separate check files, so an agent can route without opening any schema.

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?

Gives explicit when-to-use routing per operation ('save_model_file to persist current work, open_model_file to replace the active project, initialize_model to clear it for a new model') plus named alternatives for adjacent concerns and a precondition ('Inspect connection/readiness first'). Nothing is left to inference.

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