update

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

With no annotations provided, the description carries the disclosure burden. It clearly warns about data-loss risk (omitting unchanged terms causes deletions) and about aiMetadata preservation semantics, which are non-obvious behavioral traits. It also recommends AI metadata fields. It doesn't mention side effects like cascade updates or related resource reindexing, but the critical destructive behavior is well disclosed.

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 relatively compact given the complexity of the tool, front-loading the core purpose and then providing targeted warnings and recommendations. It earns its length by covering the non-obvious update semantics. It is somewhat dense but not bloated, though it could be tightened by removing redundant phrasing about aiMetadata.

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?

Given the enormous polymorphic schema with no output schema and no annotations, the description covers the most important cross-cutting behavioral rules (term preservation, aiMetadata scoping, recommended AI fields). It doesn't explicitly list all supported resources or describe return values, but the schema's conditional branches enumerate resources and output schema absence lowers the bar for return-value disclosure. For an agent, the critical update gotchas are covered.

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 compensate. It explains that payload shape varies by resource, which is essential, and details the important aiMetadata/terms semantics (full terms array, aiMetadata scoping). However, it doesn't describe the top-level 'id' or 'resource' parameter values beyond implication, and the resource list is only visible in the schema's conditionals. Still, the description adds high-value parameter context for the trickiest parts.

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 verb ('Update') and resource ('entity by ID for the given resource'), and notes that payload shape depends on resource, which distinguishes it from list/get/create. It doesn't enumerate which resources are supported, but the schema's conditional branches make that clear. It is concise and informative.

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 description gives important update-specific guidance (send full terms array, include aiMetadata only for terms to update, recommended AI metadata fields) but doesn't explicitly contrast with sibling tools like create_term or update_term. It implies usage for term-managed resources and gives clear when-to-use details, but lacks direct alternative routing.

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