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

With no annotations, the description carries the full disclosure burden and does well: it states the mutation behavior (create/overwrite), the live-theme refusal, that publishing is a separate gated step, and the sensitive-tier approval mechanics (manager approval; from-now-on vs just-once semantics). Minor gap: no mention of return values or rate limits, but the key safety behaviors are transparent.

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The description is informative but somewhat redundant: the routing line ('write a theme source file on an UNPUBLISHED theme — refuses the live theme') repeats the first paragraph almost verbatim. The sensitive-tier note is useful operational context but adds length. Well-organized into clear sections, but the duplication costs it a higher score.

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 moderate-complexity tool with all 4 params documented and no output schema, the description covers the use case, the live-theme exclusion, the separate publishing step, and approval gating — a strong operational picture. It doesn't describe the return value (no output schema exists), which is a minor gap, but given the input side is fully covered, overall completeness is good.

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% — all four params (theme_id, filename, content, companyId) are described in the schema, including the 'must NOT be the live theme' constraint, file path examples, and the 200k char limit. The description adds marginal value by naming the accepted file types (Liquid/CSS/JS/JSON) up front, but parameter detail is largely schema-borne, so 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?

Specific verb+resource: 'Create or overwrite one file (Liquid/CSS/JS/JSON source code) in an UNPUBLISHED Shopify theme.' It clearly distinguishes from siblings by noting this builds the draft theme and 'Refuses the LIVE (MAIN) theme', separating it from publish_shopify_theme and content-create tools.

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?

Explicit when to use: 'Use when a person or agent is building or editing the site's draft theme.' Also explicit when-not with an alternative: 'Refuses the LIVE (MAIN) theme; publishing a theme to buyers is a separate approval-gated step', pointing toward the publishing workflow. The routing line reinforces the unpublished-only constraint.

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