read_pawn_script

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

With no annotations, the description carries the full behavior burden. It discloses the key safety trait (`ONLY safe way to handle encoding and language`) and the corruption risk of alternatives, plus the optional line-range behavior. It doesn't mention the return format or that the operation is read-only, but the tool's name and the lack of mutation imply enough for most agents.

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?

Four short, purposeful sentences. The mandate is front-loaded, the warning is concrete, and the optional range feature is stated in a single clause. There is zero filler or repetition of schema content.

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 relatively simple file-read tool with four parameters and no output schema, the description covers the essential selection, safety, and capability information. A brief statement of the return value would have made it complete, but that omission is minor given the name and the rest of the definition.

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%, so the schema already documents all parameters. The description adds that paths should be .pwn/.inc files and that line ranges are optional, but it doesn't deepen the semantics of `encoding` or `path` beyond what the schema states. This is a solid baseline with minor added value.

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 makes it unmistakable that this tool reads .pwn/.inc files, with `MANDATORY: ALWAYS use this for .pwn/.inc files` and a mention of optional line-range reading. It distinguishes itself from generic or sibling readers by warning that standard tools will corrupt these files and by scoping to Pawn script/extensions.

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 gives explicit when-to-use guidance (`ALWAYS` for .pwn/.inc) and an explicit exclusion (`Standard tools WILL corrupt`). It doesn't directly contrast with the sibling `read_include`, but the mandatory phrasing covers the main selection scenario, leaving only a minor gap for alternative-sibling routing.

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