field_caps

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the description does not need to restae safety. It adds useful behavioral context: the tool inspect capabilities, reports tapabilities, and supports multiple fields including wildcards. No behavioral surprises are hidden, and there is no contradiction with annotations.

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 three sentences with no filler. The primary behavior is first, the motivating use case is second, and the fields parameter usage is last. Every sentence adds useful information and the syntax is flat and scannable.

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?

With an output schema present, the description does not need to explain the full return shape. The use case, parameter input, and behavioral scope are all covered. For a rea-only introspection tool with simple parameters and rich schema output, this is complete enough for an agent to select and call it.

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 description coverage is 0%, so the description must carry parameter semantics. It directly explains the fields parameter ('comma list or *') and clarifies why you would pass certain fields. The index parameter is not given a separate formula, but it is contextued by 'across indices' and the talk of index patterns, so an agent can reasonably map it to the required index string.

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 states a specific verb ('Show the capabilities'), a precise resource (fields across indices), and names the underlying API (_field_caps). It also enumerates the concrete outputs (type, searchable, aggregatable), making the tool unambiguous and distinguishable from sibling tools like get_mapping.

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 a clear primary use case: detecting fields mapped to incompatible types across indices, which breaks queries over an index pattern. It does not explicitly enumerat alternatives or when-not to use it, but the context is strong enough for an agent to know when field capabilities are relevant.

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