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

Annotations already indicate this is a mutating, non-readonly operation. The description goes beyond them by explaining the partial-patch behavior and the background re-matching side effect. It does not describe response or validation behavior, but the annotations cover the safety profile.

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 front-loads the action and the key partial-update instruction, then lists the supported fields, and ends with the background effect. It is dense due to the long field list, but every element earns its place and there is no filler.

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 nested parameter with no output schema, the description supplies the essential field list, value constraints, and post-call behavior. Minor gaps remain around response format and unknown-field handling, but the tool is callable with the information 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?

The schema only describes the patch parameter as 'Targeting fields to change, by name', leaving nested field semantics undefined. The description compensates by enumerating many valid keys, enum values (remote_mode, geo_scope), and formats (ISO-2 for geo_countries), giving the agent substantially more meaning than 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 uses a specific verb and resource: 'Change targeting rules', and the title clearly states 'Change my job targeting'. It clearly distinguishes from the read sibling get_targeting and other profile tools, so an agent can identify it as the update operation for targeting.

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 instruction 'send only the keys to change' provides clear partial-update semantics, and the note that the feed re-matches in the background tells the agent what happens after the call. It does not explicitly name alternatives or exclusion criteria, but the intended use is clear from the context.

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