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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the note that diagnostics are 'syntactic and semantic' and that they apply to 'supplied files,' implying no whole-project scanning. However, it does not disclose details like pagination behavior or that it may require a snapshot or tsconfig for accurate results. Given the annotations, a 3 is fair—some added context but not rich behavioral disclosure.

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 a single sentence, concise and front-loaded with the core action and object. Every word contributes to the primary purpose, and there is no redundancy or filler. It is appropriately brief for a tool whose purpose is straightforward, even if the parameter semantics are lacking.

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?

Given the tool's complexity—8 parameters, nested objects, a oneOf constraint, and an output schema—the description is far too sparse. It does not explain when to use it, what the parameters mean, or how to handle the oneOf alternatives. While the output schema clarifies return values, the description leaves critical context, such as the need for either files or snapshot, entirely to the schema, which has no descriptions. This is incomplete for an agent to call correctly without additional inference.

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%, meaning none of the 8 parameters (files, snapshot, limit, offset, compact, packages, tsconfig, path) have descriptions. The tool description does not compensate: it only mentions 'supplied files,' which maps to the 'files' parameter, but says nothing about the oneOf requirement, the meaning of limit/offset, or the purpose of packages, tsconfig, or snapshot. The agent would have to guess or rely on schema structure, which is insufficient.

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 clear action ('Return'), a specific resource ('TypeScript syntactic and semantic diagnostics'), and a scope ('for supplied files'). This distinguishes it from sibling tools like find_references or get_type, which focus on code navigation rather than diagnostics. The word 'bounded' hints at a limited result set, which aligns with the pagination parameters, though it is not fully explained.

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 provides no guidance on when to use this tool versus its siblings. It does not mention alternatives or conditions for selection. For example, it does not say 'Use this when you need type errors' or 'for cross-file analysis, use query_code.' The lack of context leaves the agent to infer usage from the tool name alone.

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