delete

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

No annotations are provided, so the description carries the full burden. It discloses behavioral traits: eviction of cache, handling of symlinks (deletes link, not target), normal statuses (deleted, would_delete, not_found), and constraints. This is comprehensive.

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 concise and well-structured, with purpose stated first, followed by statuses, constraints, and args. Every sentence adds value without redundancy.

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 the presence of an output schema (as per context signals), the description covers return statuses, behavioral details, and parameter semantics without needing to describe output format. It is complete for an AI agent to use correctly.

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 0%, but the description explains each parameter in detail: path is 'File or symlink path (absolute or relative to project root),' and dry_run is 'Preview without deleting or evicting cache,' adding meaning beyond the schema types.

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 starts with 'Delete one file or one symlink path and evict cache entries for that path,' which is a specific verb+resource. It also explicitly states 'Use this for explicit single-path removal instead of shelling out,' differentiating it from siblings like edit, write, and read.

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 clearly states when to use the tool ('explicit single-path removal') and lists constraints (no globs, no recursive, no real-directory delete). It does not explicitly mention alternative tools by name, but the context of siblings implies the unique role of this tool.

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