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

Annotations cover mutation/idempotency but not persistence; the description goes beyond them by disclosing that it reads the persisted `<model>.ledger.json`, rewrites that file, and marks facts as `confirmed` or `overridden`. It also states the return payload includes `paramOverrides` (factId -> value), which is exactly the kind of side-effect and output-contract detail annotations cannot express.

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?

Front-loaded with the trigger condition before the mechanics, and every clause (ledger path, resolution shapes, rewrite behavior, paramOverrides handoff, skill pairing) carries information. The main sentence is long and heavily em-dashed, which costs a little readability but not content.

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 two-parameter, non-destructive mutation feeding a multi-step workflow, the description covers preconditions, file effects, request shape, and the handoff to set_param; an output schema exists so return-value detail is not required. Nothing needed to invoke it correctly is missing.

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 already 100%, so the baseline is 3; the description earns above that by explaining the two resolution shapes in domain terms — `{ id, confirm: true }` to accept as-is versus `{ id, value }` to override — and the resulting ledger state change. It stops short of stating whether `value` and `confirm` are mutually exclusive or what happens on an unknown id.

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 and resource (resolve the open facts in an assumption ledger) and names the exact upstream tool that produces that ledger (trace_from_image) plus the downstream consumer (set_param). An agent can distinguish it from trace_from_image or set_param without opening any schema.

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 an explicit trigger — 'use this when you need to confirm or override the open facts ... before committing geometry built from a reference photo' — and embeds it in a named workflow (trace_from_image -> resolve_assumptions -> set_param, plus the kernelcad-from-reference skill). The only gap is a lack of an explicit when-not clause, but the pipeline positioning leaves little ambiguity.

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