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

Annotations already declare readOnlyHint and openWorldHint, so the description's job is to add context beyond them, and it does: it discloses that held (unpublished) changes are included in the listing and that src/ appears only when the theme builds. Those details materially affect interpretation of results. It omits pagination, ordering, and whether large themes are truncated, which keeps it below 5.

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?

It is short and information-dense, but the opening is a verbless fragment ('On one site of the account, named in site.') rather than a front-loaded statement of what the tool does. The category list is useful detail, though the prose reads as notes rather than a structured definition.

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 two-parameter list tool with no output schema, the description does decent work by naming the file categories and sizes returned. The unresolved theme parameter and the absence of any guidance on what to do with the listing (read it, edit it) leave a meaningful gap.

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 only 50%: site is documented ('as list_sites names it') but theme has no schema description at all. The description echoes site ('named in site') without adding anything, and never clarifies how theme is identified (name vs. ID, as list_themes names it?), which is the parameter an agent is most likely to get wrong.

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 the resource and scope concrete: every file of a theme with its size, enumerating templates (.liquid), partials, manifest, assets, and src/. It never states a leading verb ('list'), and it does not distinguish itself from siblings like read_theme_file or list_themes, so the agent must infer the list-vs-read split from the title.

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?

There is no when-to-use guidance and no named alternative; nothing tells the agent to call this before read_theme_file or instead of theme_history. The only pointer, 'Read pixelglass://theme-contract', directs the agent to a reference document rather than explaining tool selection.

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