ssh_shell_send

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

With no annotations, the description carries the honesty burden. It discloses that the function waits for a reaction and that simultaneous blind sends can cause a stuck session. However, it leaves out details about errors, return values, and session prerequisites.

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 economical: two efficient sentences cover the action and the workflow warning. Every sentence adds value, and the main action is stated first.

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?

Given an 8+1 8-parameter tool (actually 8), no output schema, and partial parameter descriptions, the description gives useful workflow advice but omits details like the need for an open session, how the reaction is returned, and the role of timeout parameters. It is adequate for basic use, but not 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?

The schema parameter description coverage is only 38%, but the description does not add any meaningful detail about the majority of parameters. It only mentions 'text' and 'key presses' generically, providing no new insight beyond the schema.

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?

Description states a clear action: send text and/or key presses to a session and wait for reaction. The term 'session' helps distinguish it from non-interactive sibling tools, though it does not explicitly reference aliases.

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?

It gives a usable loop workflow ('send — read — view — decide') and explicitly warns against two consecutive blind sends, which tells an agent how to use the tool. It does not name explicit alternative tools, but the general context is clear.

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