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

Beyond the annotations (destructiveHint=true, idempotentHint=false), the description discloses that the rewrite is in place, that last-modified time changes, that content is untouched, and that names are normalized to lower case. That is meaningful behavioral context the structured fields do not carry; only authorization requirements and error semantics are absent.

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?

Four tight sentences, front-loaded with the core mutation contract, then operand usage, then normalization, then side effects. No sentence is redundant and nothing important is buried at the end.

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 mutation tool with no output schema, the description covers the write contract, affected scope, and side effects well. It omits edge behavior (removing a name that does not exist) and any permission requirements, but those are minor relative to what is provided.

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 100%, so the baseline is 3, but the description adds semantics not in the schema: the set/remove maps and their combined behavior, the merge-not-overwrite contract, and the lower-casing rule that applies to both written and removed names.

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 precise verb+resource ('adds or replaces entries in an object's user metadata') and immediately defines the scope ('leaves every entry it does not name alone'), which separates it from the read-side sibling get_object_metadata and from whole-object writes like write_object.

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 explicitly instructs how to use the tool ('Pass set for entries to write, remove for names to drop, or both'), giving clear operative context. It stops short of naming when not to use this tool versus alternatives such as write_object or an overwrite-style call, so no exclusions are present.

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