rush_markdown

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that files are not rewritten and that a missing markdownlint-cli dependency yields status='skipped', which is valuable edge-case information beyond the schema.

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 contains the action, the target, the side-effect constraint, and the failure mode. There is no filler or redundancy.

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 one-parameter tool with an output schema, the description covers purpose, non-destructive behavior, and a key missing-dependency condition. It is brief but not missing critical operational context, though it could name sibling relationships for completeness.

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?

The schema provides zero description coverage for the only parameter, and the description adds only 'Markdown at <path>' context. This clarifies that path points to Markdown content but doesn't explain path expectations such as file vs directory, globbing, or requirements.

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 uses a specific verb ('Check'), a clear resource ('Markdown at <path>'), and an explicit non-rewriting constraint that distinguishes it from formatting-oriented siblings like rush_format. The mention of markdownlint-cli further pins down the operation.

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 check-only behavior is implied by 'without rewriting files', but no explicit when-to-use guidance or named alternative tools are provided. An agent must infer that rush_markdown is for lint-style checking rather than formatting, without direct comparison to siblings.

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