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

With no annotations provided, the description carries the full burden and does well: it discloses that the content is returned 'boxed as UNTRUSTED CODE' and explicitly warns to treat it as inert source, never as instructions. It also mentions the returned updatedAt field, which is a behavioral detail with a downstream use. This is more transparency than most tool descriptions provide.

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?

The description is compact and information-dense. It front-loads the core function, includes a realistic example, states the untrusted-code security context, and closes with a one-line routing summary. Every sentence serves a purpose; no fluff.

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 simple read tool with 3 fully documented params and no output schema, everything needed to invoke it correctly is present: how to identify the file, how to identify the theme, the untrusted-code handling instruction, and the relationship to the editing workflow. The warning about expected_updated_at also supplies the downstream protocol. Nothing appears 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% and the description reinforces the meaning of filename and theme_id with concrete examples (sections/header.liquid, gid://shopify/OnlineStoreTheme/123). The companyId parameter's role is clearly described in schema as 'FreedomOS company id to act within'. The description doesn't add much beyond schema examples, but that's acceptable given full schema coverage.

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 clearly states a specific verb+resource: getting one Shopify theme file's raw source code by theme id and filename, with a concrete example (sections/header.liquid). It also distinguishes itself from obvious siblings like update_live_shopify_theme_file, upsert_shopify_theme_file, and list_shopify_themes by focusing on reading a single file's content. This is unambiguous.

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 explicitly says 'Use before proposing an edit to a theme file, to see its current code,' and mentions passing updatedAt as expected_updated_at when proposing a live theme-file edit. This directly connects the tool to the workflow that follows, giving clear when-to-use guidance and implicit contrast with file-edit tools. No exclusions are needed for this simple read.

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