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

Annotations already flag destructive, openWorld and non-idempotent; the description adds real context beyond that: input may execute shell commands or modify data, requires an account-bound computer:write OAuth scope, and may trigger local owner approval. It does not describe what happens on failure or whether partial writes are possible.

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?

Three tight sentences: what it does first, then the sibling routing, then prerequisites. No filler or restatement of the title.

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 2-parameter mutation tool with no output schema, the description covers purpose, routing, risk, auth and approval requirements. Return/failure semantics are absent but largely implicit for a stdin-write operation.

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 100%, with id and text both documented, including the useful 'not a device PIN' caveat. The description adds no further meaning beyond that, so baseline 3 applies.

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?

States a specific verb and resource: 'Send text to stdin of an EXZA-owned interactive process.' It also explicitly contrasts with the sibling that reads output, so an agent can distinguish this from exza_read_interactive_process_output and exza_run_shell_command without opening a schema.

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?

Gives clear when-to-use framing by naming the alternative read tool and the condition that selects it ('to read, not to type'). It stops short of saying when a new process should be started instead, or when shell commands should go through exza_run_shell_command.

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