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

Annotations declare readOnlyHint=false and destructiveHint=false, so the mutation/safety profile is mostly covered structurally. The description still adds real behavioral context the annotations cannot convey: the scope prerequisite for writes and the asynchronous call-ID/poll pattern.

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?

Four tight sentences, each carrying distinct information (scope distinction, device generality, scope rules, return/poll pattern), with the core purpose front-loaded and zero filler.

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 generic relay with an opaque nested args object and no output schema, the description covers the essential call lifecycle: scope requirement, async return, and where to fetch the result. Minor gaps remain, e.g. how to discover valid toolName values beyond the schema's 'device manifest' note.

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%, and the scopeId schema text already states 'required for write operations', so the description's scope remark largely duplicates structured data. The args and kernelId parameters get no added semantic detail, so the baseline 3 applies.

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?

Specific verb (relay) plus resource (tool call to a kernel's device executor), and it explicitly demarcates scope with '(not OT-2 specific)' and 'works with any device type', which routes the agent away from the OT-2-specific sibling pcc_relay_tool_call.

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 clear conditional guidance: safe tools need no scope, scoped write tools require an active execution scope. It also names the follow-up tool (pcc_get_tool_result) for retrieving the response. It stops short of an explicit when-not-to-use clause beyond the OT-2 distinction.

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