write_text

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

Annotations already establish destructiveHint=true and non-idempotency, so the safety profile is covered. The description adds valuable context beyond annotations: the text is bounded, LF/TAB are the only allowed control characters, and the target must be an existing channel. This helps the agent predict behavior and constraints without contradicting any annotation.

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?

A single, two-clause sentence front-loads the core purpose and constraint, then immediately resolves the main ambiguity with send_control. Every word earns its place; 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 three-parameter write tool with a destructive annotation, the description supplies the essential selection and invocation context: what can be sent, where it goes, and when to use the sibling tool. It doesn't explain return values or error behavior, but no output schema exists and the schema's parameter descriptions cover the required details.

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 coverage is 100%, and the schema already documents each parameter thoroughly (1 MiB limit, control-character exclusion, submit semantics, channel_id provenance). The description reinforces some of this ('bounded', 'LF/TAB allowed') but adds no new parameter-level meaning beyond what the schema provides, so a baseline 3 is appropriate.

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 names a specific verb ('Deliver'), a precise resource ('one existing channel'), and key constraints ('bounded ordinary Unicode terminal text'). It also explicitly distinguishes itself from the sibling send_control by reserving control sequences for that tool, so an agent can immediately tell them apart.

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 provides an explicit usage boundary: ordinary text with LF/TAB is for this tool, while explicit controls should go to send_control. It also notes the channel must already exist, which implies first using list_channels. It does not exhaustively state when not to use it versus read-oriented siblings, but the distinction is clear.

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