Inspect Project File

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses that this is a parse-only operation, that writing to computed parameters changes nothing, that values are instance-specific and not shown, and that connections/coordinates are not reliably recoverable. This gives an agent a realistic picture of the tool's capabilities and limitations.

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?

Although longer than a one-liner, the description is tightly organized: main claim first, then use case, then explicit what-it-provides and what-it-does-not sections. Every sentence carries functional information, and the limitations are separated into a clear list, so an agent can quickly extract the critical constraints.

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 single-parameter inspection tool with an output schema, the description covers all essential context: what file it reads, where that file must live, how it differs from running the model, what results are available, and what limitations apply. Nothing an agent needs to decide whether and how to call this tool is missing.

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?

There is only one parameter and the schema already documents it at 100% coverage, so the baseline is 3. The description adds value by tying the path to the results directory, comparing it to read_output_file, and clarifying that the file must be inside that directory. This extra context makes the parameter semantics clearer than the schema alone.

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 and resource ('Разобрать сохранённый проект (.xprt)') and immediately distinguishes itself from live simulation by stating it works without COM and on Linux. It then enumerates exactly what the parse yields (block classes and parameter names) and what it does not yield (connections, coordinates, calculation), making its role unmistakable among siblings like open_project, run, and connect.

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 clearly states when this tool is useful: inspecting a foreign model without launching the SimInTech environment, and on Linux where COM is unavailable. It also explains exclusions (no connection/coordinate recovery, no calculation, no parameter values). It does not name a direct alternative tool, but the context is strong enough for an agent to select it appropriately.

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