delete_index

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

The annotation readOnlyHint: false already indicates a mutation, but the description adds key behavioral traits: it permanently deletes cached files while guaranteeing source safety, and explicitly states there is no undo. This goes beyond the annotation by explaining up-front the irreversible nature and the safety boundary.

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 short, fact-dense sentences. Each sentence adds value: purpose, safety guarantee, and irreversibility warning. There is no wasted wording or redundancy beyond reinforcing the key idea.

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 simple deletion tool with one parameter, no output schema, and limited complexity, the description is comprehensive enough. It covers the essential characteristics—what is deleted, safety, and irreversibility. It does not exhaustively list all edge cases but is complete for the use case.

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?

The schema covers 100% of the only parameter ('repo') with a clear description (owner/repo or repo name), so the description adds no additional parameter detail. It does not need to, since the schema is self-sufficient.

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 removes a repo index and its cached raw files, explicitly clarifying it never touches source documents. This distinguishes it from the many read-only sibling tools (e.g., get_doc_coverage, get_toc) and the indexing tools like index_local.

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?

It implicitly tells when to use it (to remove an index) and warns about irreversibility, but it does not explicitly contrast with alternatives or state when NOT to use it. There is no mention of reverting or updating an index in place, so the guidance is adequate but not explicit.

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