ygo_get_policy

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

No annotations are supplied, so the description carries the full burden. It does add genuine value by disclosing the return shape — verbatim text with document, version and page citations — which tells the agent results are quotable and authoritative. It says nothing about whether the corpus is local or fetched, latency, or what happens when a refresh is triggered, so the mutation/sync profile stays opaque.

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?

Two sentences, front-loaded with the corpus scope, then the output characteristic. The long document enumeration is dense but earns its place by previewing what the `document` enum addresses. No filler or hedging.

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 no output schema and no annotations, the description needs to cover behaviour and routing, and it only half does: output form is covered, but the multi-mode topic parameter (status/list/search/section/page) and the distinction from adjacent rulings tools are left entirely to the schema and guesswork.

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 100%, so the schema already explains topic modes, page, query and document. The description's enumeration of document names loosely mirrors the `document` enum and confirms the corpus scope, but it adds no syntax, mode selection, or pagination semantics beyond the schema. Baseline 3 applies.

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 identifies the resource (the official Konami judge corpus) and enumerates its documents, but never states the operation — nothing says 'retrieve', 'search', or 'read'. An agent can infer retrieval from 'Verbatim text with document, version and page citations', but that is inference, and no sibling (ygo_get_rulebook, ygo_verify_ruling, ygo_judge_scenario) is distinguished.

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?

There is no when-to-use guidance at all. Given a dense cluster of closely related rules tools (ygo_get_rulebook, ygo_verify_ruling, ygo_judge_scenario, ygo_judge_interaction, ygo_wiki), the description gives no signal about which one an agent should pick for a policy lookup versus a ruling verification.

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