skill_fixture_migrate

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the risk profile is known; the description usefully adds the apply precondition chain and the non-reclassification guarantee. However it also instructs 'retry reconcile after a partial mirror failure' while no reconcile tool appears among the siblings, which sends the agent looking for something that may not exist.

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 core purpose in one sentence, then the apply preconditions and failure handling. It is dense and mostly earns its space, though 'foreground writer' and 'reconcile' are unexplained jargon that could cost an agent a round trip.

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?

A destructive mutation with an output schema, so return values need no description; the description supplies the preconditions, safety exclusions, and recovery hint that structured fields do not. What remains thin (the 'name' parameter, dry_run mechanics) is a parameter-semantics gap rather than missing behavioral context.

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 description coverage is 0%, so all four parameters are bare strings/booleans and the description must carry the load. It illuminates 'evidence' (must be explicit fixture-purpose evidence) and 'expected_sha256' (the SKILL.md hash returned by preview), but says nothing about what 'name' identifies or how dry_run's true default interacts with the preview/apply split.

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 scope — preview (and by implication apply) a single maintainer-selected fixture candidate — which is more precise than the bare name 'skill_fixture_migrate'. It does not name or contrast any sibling such as skill_manage or skill_validate, so an agent must infer the boundary from the name alone.

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 real conditional guidance: never infer fixture status from names, apply requires a foreground writer, explicit evidence, and the hash returned by preview, and production guidance / unknown entries are never auto-reclassified. The one gap is that it never says 'set dry_run=false to apply', leaving the mapping between prose and the actual switch implicit.

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