load_knowledge_pack

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

With no annotations, the description partially covers behavior: chunking, embedding, and retrieval usage during optimize_prompt. However, it omits details on overwriting existing packs, error handling, performance implications, or side effects like data persistence.

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, front-loading the main action and then explaining chunking and source options. No wasted words, though slightly more structured formatting could improve readability.

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?

Covers core functionality (loading, chunking, sources), but lacks details on overwrite behavior, size limits, or unload mechanism. Given no output schema and basic complexity, it is adequate but not thorough.

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%, so baseline is 3. The description adds marginal value beyond schema: it explains auto-detection of source types and mentions the community pack registry, but mostly repeats schema descriptions.

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 loads a knowledge pack (markdown with YAML frontmatter) into persistent memory for semantic retrieval, specifying chunking by heading and embedding. It distinguishes from siblings like list_packs (listing) and unload_pack (unloading) by focusing on loading for retrieval.

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 when needing to load documents for semantic retrieval, lists source types and a community registry, but does not explicitly exclude alternatives (e.g., memory_remember for facts) or provide when-not-to-use guidance.

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