crosspad_settings_get

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

The readOnlyHint annotation already signals this is a safe read operation, so the description has a lighter transparency burden. The description adds the context that it targets the 'running simulator' (not static config files), which is useful. However, it doesn't disclose what happens if no simulator is running (error? empty result?), nor describe the shape of the returned settings beyond what the output schema covers.

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?

A single efficient sentence that states the tool's purpose with zero filler. No waste, and the [PC sim] prefix gives necessary context about the execution environment. This is close to ideal conciseness for a simple read tool.

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?

This is a simple parameter-less-to-one-parameter read tool with a readOnlyHint annotation and a full output schema. The description doesn't need to explain return values since the output schema exists. The main gap is lack of explicit behavior-when-no-simulator, but overall the combination of description, annotation, and schema covers the tool adequately for a read operation.

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% — the 'category' parameter has a full enum and its own description ('Settings category. Use 'all' to fetch everything.'). The tool description itself adds little about the parameter, but the schema fully documents it, so the baseline 3 is appropriate. The description's 'Read settings' doesn't repeat or add to what the schema already conveys.

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 clear verb+resource: 'Read settings from the running simulator.' It specifies the [PC sim] context and the object being read (settings). While clear and specific, it doesn't explicitly differentiate from the sibling crosspad_settings_set beyond the obvious read-vs-set contrast, though that distinction is self-evident from the name.

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 notes this reads settings from the running simulator, implying it should be used when you need current simulator settings. However, it provides no explicit guidance on when to use this vs the sibling crosspad_settings_set, no mention of prerequisites (e.g., must a simulator be running?), and no exclusions. The 'running simulator' phrase implies a precondition but doesn't spell out error behavior if none is running.

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