shell_read

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool reads the output buffer from a persistent session, implying a non-destructive operation. However, it does not describe what happens if the buffer is empty, whether reading affects the session state beyond the optional clear parameter, or if there are any prerequisites (e.g., an active connection). The description is adequate but not comprehensive.

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, front-loaded with the core action. Every phrase serves a purpose: the action, target specification, and a note on omission. There is no wasted text.

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 the tool has 5 parameters, no output schema, and several sibling tools, the description is reasonably complete but lacks details on return format or buffer behavior. It does not explain how the output is presented (e.g., plain text, structured data) or what happens if multiple commands were sent. Still, it covers the essential usage for an agent to select and invoke the tool.

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 input schema covers all parameters (100% coverage), so the baseline is 3. The description adds value by recommending alias over host, and clarifying that host can be omitted when only one connection exists. This provides practical guidance beyond the schema's parameter descriptions. The clear parameter is not mentioned in the description, but the schema already defines it.

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 tool's function: reading the output buffer of a persistent shell session. It specifies the method to select a target (alias or host) and distinguishes from siblings like shell_send (which sends commands) and exec (which runs new commands). The verb 'read' and resource 'output buffer' are specific and unambiguous.

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 provides guidance on when to use the tool (to read output) and how to specify the target (alias recommended, host as alternative, can omit for single connection). It lacks explicit exclusion scenarios or alternatives to other tools, but the context is clear enough for an agent to determine appropriate use.

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