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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent). The description adds genuinely useful behavior beyond that: whitespace normalization, a character cap, deduplication of identical restrictions, and the return shape (full restriction list). Minor friction comes from the stated 280-char cap conflicting with the schema's maxLength of 300.

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?

Three tight clauses, front-loaded with the core definition and no filler. Efficient, though the trailing negation clause is slightly awkwardly attached.

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 mutation with no output schema, the description covers return value, dedup semantics, input normalization, and scope boundaries. The unexplained brandId parameter and the 280/300 cap mismatch are the only notable gaps.

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 parameter meaning. It explains handling of 'text' (normalized, capped) but the stated 280-char limit contradicts the schema's 300, and brandId is not explained at all, leaving half the parameters undocumented.

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?

States a specific verb (add) and resource (restriction) and immediately defines what a restriction is ('something the brand never wants in its content'), so an agent can distinguish it from list_restrictions, remove_restriction, and the creator-fact tools 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?

The negative scoping clause ('Does not touch creator facts or script preferences') usefully routes the agent away from add_creator_fact and update_script_preferences, but there is no explicit when-to-use guidance and no forward reference to list_restrictions/remove_restriction as the complementary tools.

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