Write a file

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

Beyond the annotations (which only say destructive/openWorld=false/idempotent=false), the description discloses exactly what gets destroyed ('An existing file of that name is replaced'), what will fail ('parent directory must exist'), a safety guardrail blocking SYS:, C:, S:, LIBS:, DEVS:, L: locations, and the encoding transformation applied to text. That is precisely the extra context an agent needs for a destructive write.

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?

Six short sentences, front-loaded with the action and replace behavior, then encoding choice, preconditions, safety refusal, and return value. No filler or restated title, and each sentence carries a distinct constraint.

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?

With no output schema, the description covers the return value ('a line with the bytes written'), and it supplies the safety, precondition, and encoding facts a destructive 3-parameter tool needs. Nothing material for correct invocation is missing.

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%, so baseline is 3, and the description earns more by adding semantics the schema lacks: Latin-1 encoding plus LF normalization for 'text', binary intent for 'base64', and the mutual exclusion rule (no oneOf in the schema enforces it). It adds nothing about path formatting or validation beyond the schema's example and the system-place refusal.

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 opening sentence gives a specific verb and resource with scope ('Create or replace one file on the Amiga'), which is immediately distinguishable from amiga_read_file, amiga_ls, and amiga_text. Replace semantics are stated up front, so the agent knows this is a write, not a read.

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 clearly states when each content mode applies ('text' for Latin-1 text with LF line ends, 'base64' for binary) and explicitly forbids supplying both, plus preconditions (parent directory must exist). It does not name or defer to any sibling tool, but no sibling in the list offers file writing, so there is no real routing ambiguity to resolve.

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