lsp_diagnostics

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

No annotations exist, so the description carries the full burden. It usefully discloses that real compilers/checkers are executed and that output is location-aware, but omits whether the operation is read-only, whether the toolchains must be installed, expected latency, and what happens when nothing is found.

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 no filler; the concrete tool names do real work. It is however sparse for a tool with an undocumented parameter, so brevity shades into under-specification.

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 and no annotations, so the description must cover both safety and returns. It sketches the return shape ("structured, location-aware issues") but leaves the sole parameter and failure/empty-result behavior unexplained, which is insufficient for an execution-backed diagnostic tool.

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?

There is one parameter, project_root, at 0% schema description coverage, and the description never mentions it — no default (cwd?), no meaning of the path, no constraint. The single ambiguity an agent must resolve is left undocumented.

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?

Specific verb+resource ("Run language-server-style diagnostics") with concrete implementation examples (tsc/pyright/cargo check/go vet) and a stated return shape ("structured, location-aware issues"). It does not differentiate from any sibling, though run_verification is the nearest potential confusion and no contrast is offered.

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 never says when to call this versus alternatives such as run_verification or self_critique, nor any precondition (e.g. run after edits, before commit). Usage must be entirely inferred from the tool name.

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