Modify attributes

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

Annotations already cover the destructive/idempotent profile, but the description adds substantive behavior beyond them: the operation runs 'in one undo step', it is a partial update ('only the given fields change'), fonts are unsupported, and LayerCombination with base:'current' has a side effect (re-captures current layer states). These are non-obvious traits an agent needs.

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?

Front-loaded with the core purpose, then examples, then the per-type field catalog. Dense and information-rich rather than padded, though the long enumerated field list adds bulk that could be structured more scannably.

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, the description supplies the return shape ({results: [{index, name, guid} | {error}]}) and the per-type field contract, plus identifiers and an undo naming hint. There is no annotation/output-schema gap left for the caller to guess at.

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 only 50%, but the description compensates heavily: it defines the item shape ({type, attribute, name?, folder?}), the accepted attribute identifier forms, and enumerates the changeable fields per attribute type, plus concrete examples. It stops short of units/semantics for every field, deferring to the create_*/get_attributes tools.

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 ('Changes existing attributes') and resource ('of any type') with scope qualifiers. An agent can immediately distinguish it from create_* (creation), delete_attributes (removal), duplicate_attributes, and get_attributes (read) 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?

Clarifies that only *existing* attributes are affected and that 'only the given fields change', which is strong context for choosing this over the create_* siblings. It also notes a hard exclusion ('Fonts cannot be modified'). It does not, however, name an explicit alternative tool or a when-not-to-use condition, keeping it short of a 5.

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