knowledge_files

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

With destructiveHint=true in annotations, the description should explain what side effects may occur, especially given the overwrite parameter, but it does not. The word 'controlled' suggests access limits, but it adds little concrete behavioral context about mutation, overwriting, or normalization side effects.

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 a single compact sentence that front-loads the core resource and action set. There is no filler or redundant restatement of the tool name.

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 six parameters, a destructive hint, an overwrite flag, and several sibling tools, this one-line description is not sufficient context. The output schema may cover return values, but input selection, side effects, and usage boundaries are left unexplained.

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 only 17%, so the tool description must compensate for undocumented parameters like path, pattern, category, max_chars, and overwrite. It does not explain these; only the action values are loosely reflected in the description.

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 identifies a specific resource ('controlled source files and PDFs') and concrete actions (list, read, normalize to Markdown), so an agent can tell what the tool operates on and what it can do. It stops short of a 5 because it does not differentiate this tool from closely named siblings like knowledge_document or knowledge_page.

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?

There is no guidance about when to choose this tool over siblings such as knowledge_document_context or knowledge_admin, nor any mention of when to use list versus read versus normalize. The action enum hints at usage, but the description does not provide decision criteria or exclusions.

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