kernel_office_pack_export

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses the filtering rule (active, general, above confidence floor), the deterministic sort order, the redaction defaults and exactly which data classes are blanked, and that the tool returns content rather than persisting a file. Gaps remain around authorization requirements and any size/rate limits, but the core behavior is well covered.

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?

Three sentences, front-loaded with purpose, then determinism, then redaction and return value. No filler, no repetition of the tool name, and the safety-relevant detail (PII blanking) is stated in plain terms rather than buried.

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?

An output schema exists, so the description correctly avoids explaining return structure beyond noting it returns the file's content. For a single-office read tool with one required parameter this is close to complete; the notable omissions are access requirements and whether exporting is idempotent only under identical filter settings.

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 coverage is only 25%, so the description must compensate, and it largely does: it defines what the confidence floor means (min_confidence), what redaction suppresses and how to disable it (redact=false), and what the two format values produce. Only 'office' is schema-documented, but the description's phrasing anchors all four parameters to concrete semantics.

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 and resource: export an office's agent learnings as a knowledge pack, with supported formats named. The scope is narrowed further to 'active, general learnings above a confidence floor,' which is a real qualifier rather than a restatement. It does not explicitly contrast with kernel_office_pack_import or kernel_marketplace_export, though the direction is unambiguous.

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?

Usage is implied by the verb and by the git-diff-stability note, which signals repeated/versioned exports as the intended pattern. There is no explicit when-not-to-use guidance, no mention of how this relates to the sibling import tool, and no stated prerequisites (e.g., permissions or what an empty pack looks like).

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