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

The description discloses that it is free and has no side effects, that it includes both seeded and unregistered tools (with registered:false flagging for drift), and that renaming a function changes mcp_name but keeps tool_id stable. It also explains it diffs the live wire surface against registry. Rich behavioral context beyond what annotations provide (and no annotations exist to contradict).

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 fairly long (about 6 paragraphs) but each paragraph adds meaningful information: the authoritative use case, the inclusion of unregistered tools with issue references, the renaming semantics, and the wire-diff behavior. It's front-loaded with the core purpose in the first line. Slight redundancy between paragraphs 2 and 4 about drift/deploy drift, making it slightly less tight than ideal.

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?

The tool has zero parameters, an output schema, and the description thoroughly explains return values including the registered:false flags, unregistered top-level array, and the drift-detection semantics. Given the complexity of the canonical-UUID reconciliation purpose and the absence of annotations, the description fully compensates and explains the output shape and why specific fields exist.

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?

The tool has zero parameters and the schema is 100% covered (empty params). Per the rubric, 0 params = baseline 4. The description adds no parameter docs needed since there are none, but it does explain what the output contains semantically (registered:false, nested unregistered array), which aids the consumer in interpreting results.

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 returns canonical (tool_id, mcp_name, ...) for every tool the wheel exposes. It uses a specific verb ('Return') with a precise resource ('canonical tool identity list'), and it distinguishes itself from siblings by framing itself as the authoritative identity source used by Reconcile — clearly differentiating from data/list tools like schwab_list_coupons and oracle introspection tools.

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 explicitly names the consumers (Studio, agents, FE, Reconcile) and states the exact use case: UUID-join against stored pricing model, with explicit instruction 'no name-based UUID derivation, no guessing.' It also explains when not to use it implicitly by positioning this as canonical against other tools that would guess. This is explicit usage guidance with concrete exclusionary instruction.

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