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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description does add real value beyond them: it scopes results to DRAFT files and notes that each file's serving page is reported, which shapes how an agent reads the output. It stops short of pagination, ordering, or what is returned for non-HTML site formats.

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, but the second sentence ('Format: get_style_reference({ topic: "liquid" })') reads as leaked or misfiled boilerplate that does not describe this tool and actively confuses the reader. The useful content is buried in a parenthetical conditional ('format: html') that leads the description.

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 must convey what comes back — it partially does ('every draft file ... and which page each serves'). However, for a tool with 0 required params and a site-format conditional, the description never resolves what is returned for non-HTML sites or how a caller should pick a site id. Adequate but with clear gaps.

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 both id and glob are already documented in the schema, making 3 the baseline. The path examples in the description ('partials/*.liquid', 'assets/*.js') illustrate the file universe but do not clarify glob syntax or default behavior beyond what the schema says. No added semantic value over the structured fields.

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 identifies a specific resource — draft site files (pages/*.liquid, partials/, sections/, theme.css, site.json, emails/, assets/*.js) — and a notable output trait ('which page each serves'). But the verb is only implied via the name, and the scope is gated on 'HTML-first sites (format: html)' with no statement of what happens for other site formats. It does not differentiate itself from search_site_files, read_site_file, or list_pages.

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?

No when-to-use instruction is given. The closest thing to guidance is the trailing 'Format: get_style_reference({ topic: "liquid" })', which points at a different tool rather than explaining when to choose list_site_files over search_site_files or read_site_file. An agent must infer the routing from tool names alone.

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