Recursive Ops

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is partly covered. The description adds nothing beyond that: it doesn't say the operations run over SSH, that credentials come from username/identity_file/password_ref, or that some operations (delete, move) mutate or remove remote files. Given destructive operations are reachable, silence on irreversibility is a real gap.

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 two fragments are short but not concise in the useful sense: for a 24-parameter, multi-operation surface there is no structure, no grouping by operation, and no front-loaded statement of the primary mode. It is under-specification rather than economy.

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 24-parameter tool that multiplexes copy/move/delete/list/chmod/chown plus search, backup, diff, and watch parameters, two sentences of boilerplate leave an agent without the information needed to call it correctly. The output schema covers return values, but the selection logic across operations is entirely absent.

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 the baseline is 3; each parameter is already tagged in the schema with the sub-operation it belongs to (recursive_ops, content_search, backup, diff_compare, watch). The description adds no meaning on top of that, notably not explaining that 'operation' is the discriminator that determines which of the 24 parameters matter.

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?

"Recursive ops (tm_files). Advanced file operations on remote hosts." mostly restates the tool name and title; "advanced file operations" names no specific verb or resource scope. An agent cannot tell from this whether the tool copies, deletes, chmods, or backs up, and cannot distinguish it from siblings such as tm_file_backup or tm_file_content_search, which the schema itself shows are folded in here.

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 when-to-use guidance, no prerequisites, and no mention of any alternative tool. With a dozen siblings covering file search, backup, diff, watch, and remote file transfer, the description offers no basis for routing a request to this tool rather than those.

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