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

The description discloses key behavioral details beyond the annotations: nested bags (offer, product_map, icp) merge rather than overwrite, only provided keys change, and Brand Memory is untouched. This goes beyond the provided annotations, though it doesn't cover output/return behavior or failure cases.

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 short, information-dense sentences with no filler. The patch semantics, merge behavior, and concrete examples are front-loaded and directly useful.

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 single-parameter patch tool, the description covers semantics, nested merge behavior, and out-of-scope side effects. It does not describe the return value, but the input schema and provided examples make the tool sufficiently actionable.

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 already documents the 'fields' object and nested merge behavior, and the description adds concrete examples and the list of valid nested bags (offer, product_map, icp), giving practical parameter context beyond the schema alone.

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 opens with a clear verb-resource pairing: 'Patch Brand DNA.' It specifies partial updates ('Send only keys to change') and defines the object being modified, clearly distinguishing it from read operations like get_brand_dna.

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?

It gives strong usage context: patch semantics, nested merge behavior, and an explicit exclusion ('Does not read or write Brand Memory'). It stops short of naming sibling tools as alternatives or giving explicit when-to-use vs. get_brand_dna guidance, but the context is clear enough.

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