Search Tokens

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

Beyond the readOnlyHint annotation, the description discloses substantial behavioral traits: the matching algorithm (substring), the fields searched (name, description, value), the value resolution difference between BSI (raw) and DTI (resolved), and a concrete failure example. This goes well beyond the annotation's safety signal.

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 compact yet information-dense. Every sentence adds value: purpose, scope, matching behavior, examples, and a critical limitation. It is front-loaded with the core action and efficiently structured without 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 simple one-parameter search tool with readOnlyHint, the description covers all necessary aspects: what is searched, how matching works, what values are searched, and a meaningful limitation. No output schema exists, but the description sufficiently conveys the tool's behavior and expected outcomes.

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 single 'query' parameter is fully described in the schema, but the description adds rich semantics: examples of valid queries, noting that values are matched in both raw and resolved forms, and clarifying the substring-only constraint. This adds meaning beyond the schema's simple 'Search term' description.

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's action: searching for Design Tokens Italia or BSI tokens by substring match. It specifies the exact scope (BSI CSS custom properties and DTI global tokens) and provides examples, making it distinct from sibling tools like tokens_list_globals or tokens_resolve.

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 clear context for when to use the tool (to find tokens via substring matching) and explicitly notes a limitation (semantic phrases like 'primary color' will not work). However, it does not explicitly reference alternative sibling tools, so it misses the 'alternatives' aspect of a 5.

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