copy_file

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds two facts beyond them: it mutates filesystem state, and it requires the WISP_ALLOW_FILE_WRITES permission — an auth prerequisite not visible in annotations. It stops short of noting the non-idempotent behavior (repeated calls leave multiple copies) or whether an existing copy would be overwritten.

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?

Two tight sentences with the action front-loaded and the permission requirement carried in the same breath. The only soft spot is the qualifying hedge 'when supported by the panel', which adds a condition without specifying how the agent checks it.

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?

There is no output schema, so the description should say what the call returns, yet it never states the resulting copy's name or path — a real gap for a copy tool with no destination parameter. Combined with the silent non-idempotency, an agent knows the prerequisites but not the outcome, which is only minimally viable for a write operation.

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 100%, so both path and server_id are already documented, and the description adds no extra parameter meaning. Baseline 3 applies; the only notable omission is that nothing explains how the missing destination relates to the single path argument.

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 specific verb and resource: copy a file via Wisp. The phrase 'in place' signals that no destination is supplied, which is consistent with the schema having only a source path, but it leaves unclear where the copy lands and what it is named — the one thing an agent most needs to know. It is still clearly distinguishable from write_file, rename_file, and create_backup by intent.

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?

Gives an explicit use case ('create a safety copy before risky edits') plus a precondition ('when supported by the panel'). It does not name alternatives such as safe_write_file or create_backup, so an agent has to infer that this is the pre-edit snapshot option rather than the general write path.

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