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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real behavioral context: null when never published, BLOCKED masking, revision semantics, and changeStatus values (CHANGED/UNCHANGED/UNKNOWN) with the note that none of them refuse. It does not describe pagination or error behavior, keeping it short of a 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 a single run-on sentence stitched together with em-dashes and parentheticals, so the most important fact (what is returned) is not front-loaded and parsing takes effort. It is not bloated with filler, but the structure is poor for an agent scanning for the key behavior.

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 does the heavy lifting by enumerating the returned fields and edge cases (null, BLOCKED, revision, publish refusal, changeStatus), which is close to sufficient for a two-parameter read tool. The only gap is the unstated default when `archiveId` is omitted beyond the implied `site`-only response.

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%, so the baseline is 3; the description goes beyond the schema by spelling out what `archiveId` unlocks — the `publish` block (`allowed`, `reason`, `message`, refusal fields), `changeStatus`, and `archiveChanged`. This gives the agent meaning the raw schema field text does not carry.

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 states the resource (the game's sandbox page), its live state (`site.revision`), and what the optional `archiveId` adds, so an agent can tell it apart from get_publications and publish_sandbox. However, the core verb is implicit — it never plainly says 'reads' or 'returns' the sandbox state at the start, relying on the title, and the answer is buried in a dense dash-clause.

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?

It routes the agent elsewhere for one case ('how a publish request went is get_publications') and notes the refusal text matches publish_sandbox, but it never states explicitly when to call this tool versus get_submission_state or get_publications. Usage is implied rather than prescribed.

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