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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds genuinely useful read-modify-write semantics: 'Fetches the current tool and applies partial updates.' This merge behavior is consistent with idempotentHint and clarifies that fields are patched rather than wholesale replaced. It doesn't discuss consequences of setting active=false or replacing tool_config, but the core 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?

Two tight sentences with the verb+resource front-loaded and zero fluff. The minor flaw is structural: the enumeration 'name, description, or active status' reads as exhaustive when it is not, which amplifies the omission of tool_config and function_arguments.

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 sheer complexity — 6 parameters, tool_config with 7 field-type variants, function_arguments with ~10 discriminated tool configurations — the description is far too thin. It doesn't state that tool_config and function_arguments are updatable, doesn't describe error behavior (e.g., unknown tool_id), and offloads nearly everything to the schema. The output schema covers return values, but capability scope — the most decision-relevant information — is the critical gap.

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 documents name, tool_config, and function_arguments (50% coverage), but the description adds little beyond restating which fields are updatable — and it omits the two most complex parameters (tool_config, function_arguments), which carry critical non-obvious requirements already present in the schema (inline JSON, do not serialize, object discriminator). An agent reading only the description would assume those fields cannot be updated, making the omission actively misleading.

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 (Update) + resource (tool) + lookup key (by ID), and clearly distinguishes itself from read_tool and list_tools siblings. However, the enumeration of updatable fields ('name, description, or active status') omits tool_config and function_arguments — two of the five updatable fields — so the stated scope is incomplete and slightly misleading.

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: call this to modify an existing tool, and the resource name differentiates it from update_node, update_data_source, and update_prompt siblings. But there is no explicit when-to-use versus alternatives, no mention of the read_tool sibling as the counterpart for inspection, and no guidance on prerequisites or when partial updates are preferable to other operations.

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