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

Annotations already declare this a read-only, idempotent, non-destructive call, so the description focuses on what those cannot convey: the return payload ('core fields plus the raw document data') and the hard prerequisite of bridge module 8.11.0+. It also warns that UUIDs are not guessed or traversed automatically, preventing a common misuse, though it says nothing about size or truncation of the raw document.

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?

Every sentence carries a constraint, a source, or a limitation, with the scope statement front-loaded and the unsupported case last. The parenthetical UUID examples are long but disambiguating, not filler.

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 one-parameter lookup with no output schema, the description supplies the return shape, the version prerequisite, the traversal model, and the exclusion — everything an agent needs to call it correctly on the first attempt.

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 single uuid parameter is already documented with examples; the description still adds real value by constraining it to absolute-only UUIDs and naming the acceptable source of those values rather than allowing free invention.

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 opens with a specific verb and resource ('Resolve any ABSOLUTE Foundry UUID to its full document') and then enumerates exactly which UUID families are covered (world, compendium, embedded). This makes it trivially distinguishable from siblings such as compendium-document-get or actor-get.

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 explicitly routes the agent to the producing tools (compendium-browse, compendium-page-search, compendium filter tools) and explains the one-hop-per-call traversal pattern (class → granted features → effects). It also states a clear exclusion: relative UUIDs starting with '.' are not supported.

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