process_input

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

Annotations already indicate destructive, non-idempotent, non-readOnly behavior. The description adds valuable nuance: 'may execute instructions or change its state' and 'pipe-based, not a PTY'. This goes beyond the structured 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?

Two concise sentences. The main purpose is front-loaded, the operational tip is secondary, and there is no redundant content. Every sentence earns its place.

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 tool with no output schema and 0% schema parameter coverage, the description leaves too much unspecified: parameter semantics, the effect of close_stdin, and how output is retrieved (likely via process_read). It is not complete enough for an agent to confidently invoke it correctly.

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 description coverage is 0%, and the description provides no explanation of parameters such as text, offset, wait_ms, session_id, or close_stdin. The only implicit hint is that 'input' likely maps to text, but that is not spelled out.

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 states a specific action, 'Send input to a process', and clarifies its effect, 'may execute instructions or change its state'. This clearly distinguishes it from sibling process tools (process_start, process_read, process_stop, process_list) by focusing on the input-sending function.

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 clear operational context: recommends 'python3 -u -i' for a persistent Python interpreter and notes that it is pipe-based, not a PTY. It does not enumerate alternatives or exclusions, but the context is sufficient to infer when to use this tool.

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