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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, so the safety profile is covered; the description adds the useful constraints that ids must be exact, that name collisions require user resolution, and that names/recipes are user-supplied data. It stops short of describing paging mechanics or what the returned looks collection contains, which is the remaining gap.

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?

Five short sentences, front-loaded with the core action, then filtering, then edge cases, then sibling routing. Nearly every clause earns its place; the trailing "Saved names and recipes are user data" is terse and slightly cryptic, but it is a single line and plausibly load-bearing.

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, three undocumented parameters, and no return-value spec, the description does most of the necessary work: it says what is read (identity plus owned looks), where the id comes from, and how to page and filter. It would be complete if it named the cursor field consistently and hinted at what a page of looks contains.

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 0%, so the description must carry all three parameters, and it does characterize characterId (exact, sourced from list_saved_characters) and lookName (exact-match filter). However it refers to the paging parameter as "nextLookCursor" while the schema field is "lookCursor", which is a concrete mismatch an agent could misread, and it never explains the cursor's format or where a next cursor comes from.

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?

"Read the saved identity and owned looks" names a specific verb and the exact resource, and the description immediately separates it from list_saved_characters (source of the id) and from select_saved_character/prepare_recast (which take a lookId). An agent can place this tool among its siblings without opening any schema.

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 states the precondition for the required id ("exact characterId returned by list_saved_characters"), the filter options, an escalation rule ("Resolve duplicate names with the user"), and the routing rule to sibling tools for selecting a specific look. When-to-use and when-to-use-something-else are both explicit.

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