search

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

The description goes well beyond the readOnlyHint=true annotation by disclosing security-sensitive behavior: Secret content is intentionally not indexed to avoid leaking data through snippets. It also reveals query semantics (tokens AND'd), ranking, return format (ranked hits with snippets and summaryContext), and the limitation regarding warmed CRDs. No contradiction with annotations; it enriches them substantially.

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 every sentence earns its place: purpose, security caveat, examples, modifier vs. enumeration guidance, CEL recommendation, return description, and CRD limitation. It is front-loaded with the primary purpose and structured logically, with zero filler or repetition.

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?

Given the tool's complexity (5 parameters, no output schema, subtle query semantics), the description is complete: it explains what is searched, what is not (Secret values), how queries combine, how to narrow results, when to use alternatives, and what the response contains. No significant behavioral caveat is left undisclosed.

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?

Although schema_description_coverage is 100%, the description adds high-value semantics beyond the schema: explicit query syntax (modifiers like kind:Pod, ns:foo), AND logic, examples, and guidance for filter/context parameters. This transforms dry parameter metadata into actionable usage knowledge, exceeding the baseline.

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 opens with a specific verb 'Find' and defines the resource scope as 'resources by content/term match' when the user does not know which object contains a string. It clearly distinguishes itself from siblings by explicitly routing enumeration queries to list_resources and structural predicates to CEL filters, making it unmistakable what unique role this tool serves.

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?

It explicitly states when to use this tool ('when you do not know which object contains...') and when not to ('modifier-only queries are enumeration, so use list_resources', 'Use CEL filter for structural predicates'). It also provides a practical prerequisite ('cold CRDs need list_resources first'), giving clear decision guidance versus alternatives.

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