export_bundle

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write profile is covered there; the description reinforces it with the [WRITE][risk=medium] tag. Beyond that it discloses genuinely non-obvious behavioral caveats about the produced OSCAL artifact (control ids are not resolved against an imported catalog, and OSCAL has no 'partially satisfied' state), which is real added value. It still never says that out_path may overwrite an existing file, which is the concrete destructive behavior the annotation warns about.

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-loads the one-line purpose and the [WRITE][risk=medium] tag, then the format-specific caveat, then a compact Args block. The OSCAL paragraph is long but each clause (output filename, read-first pointer, two limitations) earns its place; no filler sentences.

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 destructive, non-idempotent write tool with no output schema, the description covers formats, defaults, and the OSCAL artifact's caveats well. It leaves two gaps an agent would want: whether calling it again overwrites an existing output file, and what is returned on success (a confirmation, the written path, or the document itself). Those matter precisely because destructiveHint=true and idempotentHint=false.

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 the parameter burden, and it largely does: bundle_path is defined as a bundle .json, fmt is spelled out as markdown/csv/json/oscal, and out_path's default is stated as 'alongside the bundle'. What it omits is the non-enum validation constraints (allowed extensions, wildcard behavior) and whether out_path must be an existing directory.

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?

Names a specific verb (render/export) and resource (bundle), and enumerates the four concrete output formats. It also distinguishes itself from oscal_assessment_results by positioning that tool as the way to get results inline rather than exported to a file, so an agent can separate the two without opening either 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?

Explicitly routes the agent: 'Read oscal_assessment_results first if you need the document inline plus its limitations', which names an alternative and the condition that selects it. There is no equivalent guidance for the markdown/csv/json formats or for when not to export (e.g. before verification), so the coverage is uneven rather than complete.

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