crosspad_stats

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

Annotations already declare readOnlyHint=true, so the agent knows this is a safe read operation. The description adds the list of statistics categories retrieved, which is useful context. However, it doesn't mention that the simulator must be running (an implied failure mode), the output structure, or whether stats reflect live/current state. With readOnlyHint covering the safety profile, the modest additional context warrants a 3.

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 a single tight sentence that front-loads the verb and resource, then enumerates the payload categories. Zero waste, no filler, every clause adds information. The '[PC sim]' context prefix is efficient.

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?

With 0 parameters, a readOnly annotation, and a structured output schema present, the description's burden is light. It enumerates the major statistic categories which pairs naturally with the output schema. Minor gap: it could note that simulator must be running, but given the sibling crosspad_run exists and the sim context, this is largely inferable. Complete enough.

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 are zero parameters, so there's no schema to compensate for. The description meaningfully defines what the tool returns (pad state, capabilities, heap, registered apps, active pad logic), which is the relevant semantic content. With 0 params the baseline is 4, and the description does enumerate what the output covers, satisfying this dimension.

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 reads runtime statistics from a running PC simulator, listing the specific categories (pad state, capabilities, heap, registered apps, active pad logic). The verb 'Read' plus the resource 'runtime statistics' provides clear intent. It's distinguishable from siblings like crosspad_check (verification) and crosspad_log (logs) by focusing on runtime stats, though it doesn't explicitly name a sibling alternative.

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 this is a read-only inspection tool for the running simulator but has no explicit when-to-use guidance or exclusions. It doesn't note whether the simulator must be running first (unlike crosspad_run which starts it), nor differentiate when to choose this over crosspad_capabilities or crosspad_list_interfaces. The '[PC sim]' prefix signals context but not usage conditions.

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