check_files

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds that problems are reported rather than auto-fixed, but omits output format, whether a nonzero exit is surfaced, and whether all listed linters always run or only those matching the file type.

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 zero filler; the enumerated linters are the substance of the tool and earn their length.

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 no output schema and two loosely documented parameters, the description carries real burden. It explains what runs and that problems are reported, but leaves the path/paths semantics and the result shape unexplained, so it is only marginally adequate.

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 only 50%: 'paths' carries no description at all. The description says 'on specific files' but never clarifies the relationship between the singular 'path' and plural 'paths' parameters, nor whether both are required or mutually exclusive, so it fails to compensate for the coverage 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?

The description states a specific verb ('Run') and resource ('compilers/linters') and enumerates the actual tools invoked (tsc, eslint, node --check, go vet, etc.). This is far more concrete than a bare 'check' name, though it never distinguishes itself from lsp_diagnostics, vscode_diagnostics, or run_command, which also surface problems.

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 statement of prerequisites, and no routing to alternatives despite several siblings (lsp_diagnostics, vscode_diagnostics, run_command) that overlap with static analysis. The agent must infer the selection criterion entirely.

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