Watch

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

Annotations already state readOnlyHint=false, idempotentHint=false, openWorldHint=true, so the safety profile is partly covered, but the description adds nothing: it doesn't explain that watching monitors paths for a duration, what triggers a result, whether the session blocks, or what credentials are needed (username/identity_file/password_ref in the schema go unmentioned).

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?

It is short and front-loaded, but the second sentence ("Advanced file operations on remote hosts") is filler that doesn't earn its place and arguably mischaracterizes a watching tool as a general file-operations tool.

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?

A 24-parameter tool with an output schema and openWorld/destructive annotations needs the description to at least explain the watch behavior and scope; instead it supplies one tautology and one generic clause, leaving an agent unable to tell what this call actually does.

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. The description adds no meaning, and given the schema is a 24-parameter union spanning watch/recursive_ops/backup/diff/search, guidance on which parameters apply to Watch (watch_paths, duration, remote_host) would have been highly valuable.

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?

"Watch (tm_files)" essentially restates the tool name and title, and "Advanced file operations on remote hosts" is a vague generic phrase that describes the whole tm_file_* family, not this tool. Nothing distinguishes watching files from siblings like tm_file_diff_compare, tm_file_backup, or tm_file_content_search.

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?

No indication of when to use Watch instead of the many sibling file tools, no prerequisites, and no exclusions. The only implied context is the generic "remote hosts," which applies equally to every sibling.

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