ssh_upload

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

With no annotations, the description carries the full burden and does substantial work: it discloses that any process-readable file leaves the machine, the 30s pool-wait behavior under SSH_MCP_MAX_POOL_SIZE, and the important exemption from SSH_MCP_COMMAND_WHITELIST/BLACKLIST with a concrete `^rm` example. It does not say whether an existing remote file is overwritten or the call fails, nor what the tool returns, which is a meaningful gap for a write operation.

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?

Front-loaded with the action, then the security and concurrency constraints in descending priority, with no filler. The final policy-exemption sentence is long but earns its length by preventing a real mistaken assumption about blacklists.

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 7-parameter mutation tool with no annotations and no output schema, the description covers the safety surface, concurrency behavior, and policy scope well. The remaining gap is overwrite/failure semantics and what a successful call reports, which an agent would want before re-uploading to an existing path.

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 coverage is 100%, so the baseline is 3; the description rises above it by scoping `localPath` as "agent-chosen" and emphasizing that any readable file is exfiltrated, which is security-relevant meaning the schema's neutral one-liner does not convey. It adds no new detail on `remotePath`, `port`, or auth parameters, but those are already fully documented.

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 opening sentence gives a specific verb and resource ("Upload a local file to a remote host via SFTP") and explicitly positions it as the mirror direction of ssh_download. However, it never distinguishes itself from ssh_write_file, the closest sibling, so an agent must infer the boundary between uploading a local file and writing remote content.

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?

Usage is only implied through the ssh_download comparison and by naming ssh_exec/ssh_multi_exec as the tools governed by command policy. There is no explicit "use ssh_upload when X, use ssh_write_file when Y" guidance, leaving the most ambiguous sibling relationship unresolved.

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