Export Saved Objects

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds valuable behavior beyond them: the result is a server-side NDJSON file with an opaque handle rather than inline content, and the readable scope is bounded by the API key's privileges rather than this tool. It does not, however, describe file lifetime, size limits, or pagination of the underlying export.

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?

Front-loaded with the core action and the key distinction (returns a handle, not content), followed by the parameter-selection constraint and the space note. Dense but nearly every sentence carries load; the terse backtick fragments are slightly abrupt but not wasteful.

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 four-parameter export tool with an output schema present, the description supplies the workflow (handle to import), the space context, and the parameter-selection rule, so an agent can call it correctly. The only material gap is the unexplained include_references_deep parameter, plus non-essential export mechanics that the output schema can cover.

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 compensate, and it does for three of four params: space (targets a Kibana space by id, defaults to default space), types (with concrete examples and the ["*"] wildcard), and objects (list of {"type":…, "id":…}), plus the exclusivity rule between types and objects. include_references_deep is never explained, leaving one undocumented parameter.

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 (export) and resource (saved objects: dashboards, data views) and, crucially, clarifies the output shape: an NDJSON file on the server plus a summary and opaque handle, not the content itself. It explicitly names the sibling it feeds (import_saved_objects), so an agent can distinguish export from import and from search/get tools without opening a schema.

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?

Gives clear conditional guidance: select EITHER types (e.g. ["dashboard"] or ["*"] for the whole space) OR objects, not both, and explains that the returned handle is passed to import_saved_objects. It also notes the space-default behavior. It stops short of stating when NOT to use this tool versus read-only siblings like search_dashboards or get_dashboard.

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