xd_project_overview

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

With no annotations, the description carries the burden and does disclose real behavioral limits: recursion stops at 3 levels and results cap at 60 files, and paths must be inside allowed roots. What it doesn't say is whether hitting those limits truncates silently or is reported, which matters for an agent that might summarize an incomplete set.

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?

One sentence plus a short limits clause. The action and the per-file summary fields come first, with the depth/file caps tacked on at the end where they belong.

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?

There is no output schema, so the description must describe returns — and it does, listing name, size, artboard and component counts, and prototype presence. The only gap is the truncation/pagination behavior when the 3-level or 60-file limits are hit.

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 100% for the single 'folder' param, so the baseline is 4, and the description earns that by adding the constraint that the path must be inside allowed roots — a semantic the schema does not state. No syntax or format detail is added beyond 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?

States a specific verb and resource ('Scan a folder ... for .xd files and summarize each') and enumerates exactly what the summary contains. The folder-level, bulk-scan scope cleanly separates it from the per-file siblings (xd_get_artboard, xd_extract_text, xd_list_components).

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?

Implies the use case (get a quick inventory of every .xd file in a directory) and flags the 'inside the allowed roots' restriction, but never states when to prefer it over siblings such as xd_list_entries or when to drop to a single-file call. Usage must be inferred from scope rather than read.

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