shell_read

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint. The description adds significant non-annotation behavioral context: the VM lock side-effect and the need to unlock. It also clarifies bounded output and long-polling behavior. No contradiction.

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?

Two efficient sentences: the first front-loads the core action and key modifiers; the second adds a necessary caution. No filler or redundancy.

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 read operation with strong annotations, the description covers the essential behavior, the locking side-effect, and parameter hints. It omits return format and error cases, but given the tool's simplicity and the annotations, it 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 has 0% description coverage, but the description maps all four parameters conceptually: 'after a cursor' to after_cursor, 'bounded output' to max_bytes, 'long-polling' to wait_ms, and 'this session' to session_id. This compensates for the lack of schema descriptions, though it does not detail parameter interactions.

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 uses specific verb 'Read' with a clear resource ('output after a cursor from an interactive shell'). It adds scope modifiers ('bounded', 'optionally long-polling') and is easily distinguished from siblings like shell_write, shell_terminate, and shell_close.

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?

Clearly implies usage after interacting with a shell session and includes a critical usage caveat: VM remains locked, so call vm_unlock when finished. It does not explicitly name alternatives or exclusions, but the context is unmistakable.

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