lsp_diagnostics

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that diagnostics come from a live language server and that all:true widens the scope, but omits any note on the 30s waitMs latency, server-not-ready behavior, or result format.

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 dense sentences, front-loaded with purpose and backends, then the one parameter caveat that matters. No filler.

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?

No output schema exists, so return shape is unaddressed, and the ambiguous path/paths pair plus waitMs timing semantics are unexplained. Adequate for a read-only tool but short of what an agent needs to call it precisely.

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% across 4 parameters, so the description must carry the burden. It only explains 'all' (returns diagnostics for other project files) and leaves path vs paths selection and the waitMs timeout default undocumented — the latter being important since a 30s wait implies asynchronous server startup.

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?

States a specific resource (compiler/type-checker diagnostics) and names the concrete backends (gopls, typescript-language-server, pyright). The phrase 'no VS Code needed' implicitly distinguishes it from the sibling vscode_diagnostics, so an agent can route correctly.

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 implies when to use it (real language-server diagnostics without VS Code) but gives no explicit when/when-not against the near-identical sibling vscode_diagnostics, nor guidance on file vs directory scope. Usage is left to inference.

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