ssh_upload_file

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

Annotations declare readOnlyHint=false and destructiveHint=true, but the description adds critical behavioral details beyond them: 'replacement is atomic and backed up by default' discloses the write semantics and safety net, and 'SSH credentials are private server-side configuration' clarifies authentication constraints. This significantly enhances the agent's understanding of side effects without contradicting the annotations.

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 description is two sentences long, with the core purpose in the first sentence and usage constraints in the second. It wastes no words, front-loads the action, and integrates all essential guidance without redundancy. Every clause contributes to effective tool selection or invocation.

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 file-upload tool with 5 parameters and no output schema, the description covers the key operational aspects: absolute local path, atomic replacement, backup behavior, credential privacy, and the alias resolution via ssh_list_servers. It also aligns with the destructive annotation, preparing the agent for overwrites. Given the moderate complexity and presence of annotations covering read-only/destructive flags, this is sufficiently complete.

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 only 40% (server and timeout have descriptions; localPath, remotePath, createBackup do not). The description compensates by clarifying that localPath must be absolute, and by mentioning atomic replacement and backup defaults that relate to createBackup and remotePath behavior. While remotePath semantics aren't explicitly detailed, the description's context plus intuitive naming cover most gaps. It adds meaningful info beyond the schema for the undocumented parameters.

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 description clearly states the action ('Upload a local file to the selected remote server through SFTP'), specifies the resource types (local file, remote server), and distinguishes it from siblings like ssh_download_file and ssh_write_file by naming the SFTP transport and the upload direction. It also adds specifics (absolute path, atomic replacement, backup) that reinforce the purpose.

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 description gives explicit usage guidance: it instructs to never ask the user for a password, and it directs the agent to use ssh_list_servers when an exact configured alias hasn't been supplied. This clearly delineates when to use this tool versus the listed sibling. It also implies the prerequisite of an exact alias, providing a decision rule.

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