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

The description discloses important behaviors beyond the annotations: the 0-100 score with critical caps (59/49/39), the output structure (issues with severity, category, file:line, fixes), and the consumption of the calling agent's context and model allowance. It also states that normal-case reviews are cheap. The annotations are all false and provide no behavioral hints, so the description carries the burden and does so well. It doesn't explicitly address the readOnlyHint=false, leaving a slight ambiguity about potential side effects.

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?

The description is dense but well-structured, leading with the core purpose, then the scoring output, then usage guidance. Every sentence carries useful information, but it is longer than strictly necessary. It also clearly front-loads the most critical facts an agent needs for selection.

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 complex tool that already has an output schema (not shown here), the description covers the essential contextual information: when to use, when to ask for permission, cost implications, file scope, and the meaning of the output score. There is nothing an agent needs in order to decide whether to call this tool that is missing.

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 already documents both parameters (files and context) with 100% coverage, so the baseline is 3. The description adds value by specifying supported file types (React, Vue, Svelte, CSS) and clarifying that 'handful of files' is the normal case, which informs how the agent should populate the 'files' parameter. It doesn't delve into the 'context' parameter, but the schema covers that.

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 clearly states the tool 'Run a Rams design review over UI files' and lists supported types (React, Vue, Svelte, CSS). This is a specific verb and resource, distinctly different from sibling tools like quick_review or usage. An agent can immediately understand what the tool does and when it applies.

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 provides explicit usage guidance: 'Call it whenever UI code has been written or changed' and gives specific scenarios (before committing, when asked about design, after editing). It also defines when to ask the user: 'Only a whole-codebase audit... is worth checking with the user'. It mentions cost and file-count norms. However, it does not explicitly name alternatives, so it stops short of a 5.

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