vscode_diagnostics

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered structurally. The description contributes the useful 'Live' qualifier, implying diagnostics reflect current editor state rather than a persisted snapshot, but adds nothing about freshness, staleness, or what happens when no server is attached.

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?

A single front-loaded sentence with the resource first and the scoping qualifier in parentheses. No filler, no restatement of annotations.

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 zero-required-parameter, read-only diagnostic query with full annotation coverage and no output schema, this is nearly sufficient. What is missing is the relationship to lsp_diagnostics and the expected return shape (severity/files grouping), which matters more here than for a trivial read.

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 coverage is 0%, so the description carries the burden, and it does: 'optionally filtered to one file' tells the agent the single 'file' parameter is optional and scoping, not required. It does not specify path format (absolute vs workspace-relative), which is the remaining gap.

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 concrete verb-resource pair: compiler/linter errors and warnings sourced from VS Code language servers, with an optional file scope. It is distinguishable from file-reading siblings, but it never addresses the near-identical lsp_diagnostics sibling, leaving overlap ambiguity.

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, no prerequisite (e.g. whether the editor/language server must be running), and no direction to alternatives such as lsp_diagnostics for the same information. Usage must be inferred entirely from the name.

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