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

The description goes well beyond the readOnlyHint annotation by disclosing the return structure (findings[], refDocs[]), the behavior for large tables (inline content vs fetch), and the matching algorithm (exact first, ILIKE substring fallback). It explains how to chain with get_document for findings, adding contextual guidance not visible in the schema or annotations.

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 long but well-structured. It is front-loaded with purpose and usage, then systematically details return values and special cases. The later details on refDocs and findings are essential for correct invocation, earning their place. A slight trim could improve conciseness, but the organization is clear.

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 an output schema available, the description still adds substantial context: it enumerates every return field (name, hash, namespace, return type, params, etc.), explains how to interpret refDocs inline vs fetch, and shows how to follow findings for deeper investigation. This is complete for the tool's complexity, and no crucial behavior is omitted.

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?

The schema already covers 75% of parameters, and the description adds meaningful detail: it notes case-insensitivity and optional 0x for hash, and clarifies the fallback behavior ('ILIKE substring') that is only implied in the schema. However, the 'limit' parameter is not described, though its min/max/default are in 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 clearly states the tool's purpose: 'Resolve a RedM/RDR3 SCRIPT native by hash or name'. It distinguishes from siblings by explicitly excluding game-data hashes and directing to 'grep_docs'. The specific verb 'Resolve' plus resource 'native' makes the scope unambiguous.

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 gives explicit usage triggers: 'Use whenever you see Citizen.InvokeNative(0x...), Citizen.invokeNative('0x...'), GetHashKey('NAME'), or a SCREAMING_SNAKE_CASE native name'. It also provides a clear when-not-to-use with alternative: 'NOT for game-data hashes (weapon/ped/animation names) — use grep_docs'. This fully addresses selecting between alternatives.

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