get_entity_assetsList assets linked to an entity (role, signed_url, versions). entity_type inventory_item → inventory. ($0.10; API key required)
| Name | Required | Description | Default |
|---|---|---|---|
| entity_id | Yes | ||
| asset_type | No | ||
| entity_type | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | ||
| assets | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry readOnly, idempotent, and non-destructive hints, so the bar is lower. The description adds useful behavioral context: a cost ($0.10), an API key requirement, and likely asset attributes (role, signed_url, versions). No contradiction with annotations exists.
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 description is concise and front-loaded, with the core action first and cost/auth tucked into a parenthetical. Every sentence contributes information without redundant fluff.
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?
The output schema and safety annotations cover some context, but the description does not define valid values for asset_type or how entity_id should be constructed. The entity_type mapping is ambiguous and an agent would likely need to guess acceptable inputs.
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?
The schema has 0% description coverage and no enums, so the description must carry parameter meaning. It partially explains entity_type with 'inventory_item → inventory', but it is silent on entity_id and asset_type, leaving a required parameter and an optional filter value underspecified.
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 states a specific action and resource: 'List assets linked to an entity', and enumerates returned fields (role, signed_url, versions). It clearly distinguishes itself from single-asset getters like get_asset by using 'list', though it doesn't explicitly name sibling alternatives.
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?
No when-to-use guidance, exclusions, or alternatives are provided. The mapping 'entity_type inventory_item → inventory' hints at one accepted value but does not help an agent decide between this and sibling tools such as get_asset, attach_asset, or upload_asset.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resources, but get_context_pack and get_life_context overlap heavily, and get_money_between_people is an intentional duplicate alias of get_person_transactions. The rest are mostly clear due to explicit descriptions.
Naming is predominantly verb_noun snake_case with clear families (get_*, log_*, update_*, search_*, notable_*). Minor inconsistencies: create_person breaks the add_inventory_* pattern, and one-off verbs like record_, attach_, merge_ are not part of a uniform scheme.
With 64 tools, this far exceeds the 50+ extreme threshold. The broad personal-life domain justifies many tools, but the count creates significant selection overhead and feels bloated, especially with redundant aliases and overlapping context pack variants.
The set covers inventory, CRM, events, food, expenses, travel, places, photos, Gmail, and notable-people lookup with strong read/write/search coverage. Minor gaps include no delete operations for events/people/food (only archive/update) and no explicit place creation.