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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description goes beyond that by disclosing the dual-mode response: a definition list by default, and an additional `character_variables` array of `[{key, value, text}]` when a UUID is supplied, plus `type`/`multi`/applicable character types for each variable. Auth needs, pagination and limits are not addressed, which is minor for a read-only metadata call.

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?

The structure is front-loaded: the resource and its fields come first, the conditional character_uuid behavior last. The field enumeration is long but each item conveys real information about returned data; the parenthetical numeric-type warning is dense but earns its place.

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?

There is no output schema, so the description must carry the return shape, and it does so concretely down to the `[{key, value, text}]` element structure. What is missing is modest: how to obtain a valid `character_uuid` and whether the definitions are static or filtered by anything else.

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 carries the full burden for the single parameter, and it does explain the semantic effect of `character_uuid` (switches on returning that character's filled values). It does not say where a UUID comes from (e.g., list_characters) or that omitting it yields only the definitions, leaving a small inference gap.

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 fields returned (age_years, height_cm, eye_color, body_type, hair_color, skin_tone, look fields), so an agent knows precisely what it retrieves. It distinguishes itself from other variable getters (get_advertisement_variables, get_lead_variables, get_rule_variables) by the resource name, though it never explicitly contrasts with them.

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 implied rather than stated: the agent must infer that this is a schema-discovery call made before editing or filling a character. The one genuine guideline given is the numeric-coercion rule (send a numeric value, never text for age_years/height_cm/weight_kg), plus the conditional effect of passing `character_uuid`. There is no explicit 'use this before X' or 'do not use this to fetch a character'.

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