references

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

With no annotations, the description carries the full burden. It adds genuine behavioral detail: the cross-file index path for CSS custom-properties/id/class tokens and the per-root scoping limit with a same-root fallback. But it omits general behavioral facts such as read-only nature, whether declarations are included by default, or result/ordering behavior, so it is only partially complete.

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 core action is front-loaded in the first sentence, and the dense second paragraph is devoted to non-obvious positional and routing details rather than filler. It is somewhat information-packed but each clause earns its place.

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 position-based query tool with no annotations and no output schema, the description covers the risky part (coordinate semantics and special-case routing) but leaves the include_declaration flag unexplained even though it directly affects the result set. Adequate but with a clear visible gap.

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 0%, so the description must compensate. It does this well for line/column (1-indexed, UTF-16 offset, tab counts as one character), which is high-value semantics absent from the schema. However include_declaration and file_path receive no explanation, leaving two of four parameters 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?

States a concrete verb+resource+scope: "Find all usages of the symbol at a position across the workspace." An agent can distinguish this from definition or hover. It does not, however, contrast itself against close siblings like callers or implementations, which also report usage-like relationships.

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 implies usage (find usages when you have a position) but never states explicit when-to-use/when-not versus callers, implementations, or definition. It does give one routing rule — CSS/HTML tokens resolve via the cross-file index rather than the single-file language server — but general selection guidance is absent.

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