knowerage_generate_bundle

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

With no annotations, the description discloses key behaviors: writes multiple files, validates paths against workspace, splits into parts based on size limits, and produces a manifest. It references contracts for limits but omits error handling details.

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 four sentences, front-loaded with the main purpose. It is concise but could be restructured for more immediate scanning of key points like output files and validation.

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 only two parameters and no output schema, the description covers output file structure, splitting logic, path validation, and mentions size limits via contracts. It is reasonably complete for a file generation tool.

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 100%, but the description adds meaning: analysis_paths are relative .md files with order preserved, output_dir is relative and determines file names. It explains how parameters influence output structure (e.g., part suffixing).

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 clearly states the tool exports analysis markdown files into chunked bundles (like NotebookLM), specifying output files and splitting logic. It distinguishes from sibling tools that handle coverage, registry, or individual document operations.

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 implies usage for exporting analysis files as bundles and mentions validation and limits, but does not explicitly state when not to use or compare to sibling alternatives like knowerage_create_or_update_doc.

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