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

Annotations already declare the mutation/non-idempotent/closed-world profile, so the bar is lower. The description adds real context beyond them — that profiles are caller-owned, that routing will not fabricate capacity or energy evidence, and therefore that the caller must supply the evidence — but it says nothing about duplicate registration behavior despite idempotentHint=false, nor about validation failures.

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?

Three dense sentences, front-loaded with the verb and resource, then the taxonomy, then the evidence contract. No filler, though the enumeration in sentence two is long enough that it reads as a list rather than prose.

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?

An output schema exists, so return values need not be described. However, for a non-idempotent write tool taking an opaque nested object, the description omits the two things an agent most needs: the trigger condition for calling it and the consequence of registering a conflicting or duplicate profile.

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 0% and the required 'profile' object is an opaque additionalProperties bag, so the description carries the load — and it does, enumerating the meaningful fields (quality, reliability, capabilities, token costs, latency, locality, energy/power, carbon intensity, cache confidence/age). Only 'request_id' remains undocumented, and the field list is illustrative rather than prescriptive about types or required keys.

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 a specific verb ('Register') and a well-scoped resource ('a caller-owned Wu Wei execution profile') and enumerates the profile kinds (reuse/cache, rule, local model, tool/workflow, cloud model). This is clearly distinguishable from routing/evaluation siblings like route_task or record_route_outcome, though the description never explicitly contrasts with them.

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?

There is no statement of when an agent should register a profile versus use route_task or record_route_outcome, nor any prerequisite or ordering guidance (e.g. 'register before routing'). The closing line about routing hints at a downstream relationship but never converts that into an actionable trigger.

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