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

No annotations are provided, so the description carries the full burden. It openly states 'Free, no side effects,' explicitly naming the tool as safe and non-mutating. It also discloses the diff behavior against the live FastMCP wire surface and the unregistered flag semantics, being transparent about what the tool reports beyond a simple list.

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 well-structured with sections covering purpose, use case, canonical-UUID rationale, drift detection, and safety. It's longer than strictly necessary but every sentence adds value — the canonical-design explanation and the drift-flag rationale genuinely help the agent understand the tool's role. It front-loads the core purpose and adds detail afterward.

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?

There is an output schema present, so return value details don't need to be in the description. The tool is complex in purpose (canonical identity, drift detection, unregistered reporting) and the description fully explains the nuance, references issues (#174, #175), and states safety explicitly. Complete for a read-only introspection tool.

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 takes zero parameters, so the 100% schema coverage trivially suffices. The description adds context about the output shape (registered true/false, top-level unregistered array) which enriches understanding of what's returned, though it doesn't need to document parameter semantics since there are none.

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 opens with a specific verb+resource: 'Return canonical (tool_id, mcp_name, …) for every tool the wheel exposes.' It clearly describes what the tool does, who it serves (Studio, agents, FE), and distinguishes its canonical-UUID role from sibling tools which operate on weather data, coupons, pricing, etc. This uniquely positions the tool in a large sibling set.

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 states this is 'the authoritative source for any client' needing to know how the MCP identifies its tools, and describes the Reconcile UUID-join use case ('no name-based UUID derivation, no guessing'). It also explains the unregistered/registered:false behavior with issue references, giving clear guidance on when and why this tool matters.

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