list_project_skill_matches

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds value beyond those by explaining the ledger is worker-verified, shadow-scoped, and has no production-write or governance authority. This context is not redundant with the annotations and helps the agent calibrate the tool's trust boundaries.

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 compact and front-loaded: the first sentence states exactly what is read, and the second sentence provides essential scope and exclusions. Every sentence earns its place, and there is no filler or repetition of schema fields.

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?

With output schema present and annotations covering the read-only, idempotent, and non-destructive profile, the description supplies the domain context an agent needs: what the ledger compares, that it is worker-verified, and that it is not an authority for downstream actions. The main gap is parameter semantics, particularly limit, but this is not fatal for a list operation.

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 the description needed to explain the parameters. It only implies project_id via 'project's' and says nothing about limit, default behavior, pagination, ordering, or how the returned entries are selected. The agent is left with only field titles and the default value from the schema.

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 and resource: 'Read the project's worker-verified shadow Training Arena ledger.' It then clarifies the ledger's scope by describing the compared arms and explicitly listing what it is not, which helps an agent distinguish it from production-facing or training-readiness 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 says the ledger 'is context for later governed decisions' and gives a long list of when-not-to-use cases such as 'business attribution, training readiness, a production winner, promotion, policy activation, dispatch, action.' It does not name alternative sibling tools, but the exclusions are explicit and useful.

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