files_delete

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses the empty-folder precondition, the specific failure mode (``not_empty`` with nothing deleted), the confirmation prompt, and a real side effect: SQL Editor tabs keep the deleted file's text as unsaved. That is meaningful operational context; the only soft spot is the deferred "same limits as files_rename" cross-reference the agent must resolve elsewhere.

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?

Three tight sentences, scoping constraint front-loaded, no filler. The dangling "same limits as files_rename" reference is the one sentence that spends tokens without paying off on its own.

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 destructive single-target operation with annotations and no output schema, the description covers failure behavior and side effects well. It is nevertheless incomplete: all three parameters, including the concurrency guard, are left undocumented, so an agent cannot fully reason about a safe invocation from the description alone.

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% for three parameters, and the description mentions none of them. It never explains `path` format, what `kind` (default "sql") selects, or that `expected_modified` is an optimistic-concurrency guard whose mismatch likely blocks the delete — a non-obvious argument an agent could easily misuse.

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?

States a concrete verb and resource: delete exactly one file, or one empty folder, on this computer, and anchors it to a familiar UI action ("the file browser's Delete"). The qualifier "on this computer" implicitly separates it from the Viya-side siblings (viya_files_delete, viya_files_rename), though it never names them.

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 file-browser context and the note that the app confirms first hint at when to reach for this tool, and "Same limits as files_rename" implies a shared precondition set. There is no explicit when-not guidance and no direct routing away from viya_files_delete for remote paths, so the agent must infer scope.

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