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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it lists exactly what disclosure flags are checked, notes that registry scan status is attributed to the registry, and explicitly states 'Read-only.' It also warns that 'no flags is not a clearance,' which is a meaningful interpretive caveat beyond the annotations. Minor gap: no mention of rate limits or pagination, but the return shape is described.

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 a clear USE WHEN trigger, a compact list of disclosure dimensions, a return-format note, a caveat paragraph, and three concrete examples. It's longer than minimal but every sentence earns its place. The examples are front-loaded near the end and are highly instructive. Slight redundancy: the return JSON is described in prose and then shown in the JSON block, but this is acceptable for clarity.

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 read-only search tool with 6 optional parameters, 83% schema coverage, and no output schema, the description is remarkably complete. It explains the return shape, the meaning of disclosure flags, the caveat about disclosures not being verdicts, and provides usage examples. An agent can correctly select and invoke this tool without needing additional context. The only minor omission is pagination behavior, but the limit parameter and return shape cover the essentials.

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 83%, so the schema already documents most parameters. The description adds meaning by showing how parameters combine in examples (query + disclosure_flags filtering, flag as a direct filter, slug for targeting a listing). It also explains the semantic meaning of disclosure_flags in the return object, which the schema doesn't fully convey. The flag enum values are listed in the schema, but the description gives them context (what they mean for safety).

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 states a specific verb ('Check what a crypto agent skill does before installing it') and resource (agent skills from ClawHub and skills.sh with static DISCLOSURE flags). It clearly distinguishes from siblings like onchain_agent_search_agents by focusing on pre-install disclosure inspection rather than general search. The USE WHEN trigger makes the purpose immediately actionable.

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 says 'USE WHEN someone is about to install an agent skill and should know what it will touch first' and provides concrete examples mapping natural-language intents to parameter usage (e.g., 'solana skills that don't touch keys' -> query + filter disclosure_flags). It also clarifies that a disclosure is not a safety verdict, preventing misuse. This is strong when-to-use guidance with alternatives implied by sibling names.

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