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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating (the leading '[read]' is redundant). What the description genuinely adds is the response shape in both modes, which matters because there is no output schema. Failure behavior for an unknown uuid is still undisclosed, so it falls 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?

Two sentences, dense and front-loaded with the default (param-less) return, followed by the conditional augmentation. The parenthetical field list is long but every element carries information; only the bracket tag '[read]' is wasted ink.

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-optional-param read tool with no output schema, the description covers both response shapes and the field-level meaning of the returned variables (`type`, `multi`, applicable character types, allowed codes). The remaining gap is provenance of `character_uuid` and any error/empty-state behavior.

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 0%, so the description must carry the semantics of the single parameter, and it does: `character_uuid` is the switch that adds a `character_variables` section rather than changing the primary result. It stops short of stating the uuid format or where to source it (get_character / list_characters).

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 names the exact resource (`character_appearances` variables) and enumerates the concrete fields returned (height_cm, weight_kg, eye_color, etc.), plus a second mode returning a character's filled `[{key, value, text}]` values. That is far more specific than a tautological 'Get Character Variables'. It does not explicitly contrast with near siblings like get_character or get_image_variables, keeping it below a 5.

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?

Usage is only implied through the conditional clause 'With `character_uuid` it also answers...', which tells an agent that omitting the param returns definitions only and passing it adds the character's filled values. There is no explicit statement of when to prefer this over get_character or list_characters, nor any prerequisite for obtaining a uuid.

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