list_tokens

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

With no annotations, the description carries the full behavioral burden and delivers substantial domain context: source file, expected total counts, removal of radius tokens, and which tokens components actually read (e.g. 'cia.space(4) → var(--space-4)'). It does not disclose operational traits like default pagination or filter interaction, but the semantic warnings prevent real theming mistakes.

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 long but front-loaded with the core purpose, then counts, then categories, then two dense notes. Every sentence earns its place — the spacing and radius warnings are directly actionable and would be costly to omit — though an agent must parse several clauses before reaching the filter-relevant category list.

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 list tool with no output schema and no annotations, the description covers the domain thoroughly: what is listed, the source, the scale, and deprecated items. Minor gaps remain around default behavior when no filters are supplied, whether filters combine, and ordering/pagination semantics.

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 25% (just the 'required' param), so the description must compensate. It does so strongly by listing all 17 valid category values and giving count context that makes limit/offset meaningful, plus clarifying required vs optional totals that map to the 'required' boolean filter.

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 — 'List the CSS custom-property tokens in the theme contract (scripts/theme-contract.json)' — with concrete scope (127 required + 41 optional = 168 total) and enumerated categories. This clearly differentiates from siblings like get_token (single lookup) and search_tokens (filtered search).

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 gives rich context on how to interpret the token data (theme the numbered space scale, not the aliases; avoid removed radius tokens), but says nothing explicit about when to choose list_tokens over search_tokens or get_token. Tool-selection guidance is only implied by the word 'List' and the sibling names.

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