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

Annotations already declare a non-read-only write. The description adds genuinely useful behavior beyond that: the merge semantics (send only what changes, so unspecified preferences are preserved) and that the change influences match ranking and Autopilot. It does not state permissions or reversibility, but the merge disclosure is meaningful.

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 very short clauses, front-loaded with the action and the merge rule, with zero filler. It is terse to the point of being slightly cryptic, but every clause carries information.

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 an 11-param all-optional mutation with no output schema, the definition covers the essentials: merge behavior, downstream effect, and a pointer to the human-readable result in `say`. Missing only explicit guidance on sibling selection and side effects of clearing values.

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 description coverage is 100%, so all 11 parameters (including the nested pay_floor object and enum-like value lists) are already documented in the schema. The description adds no per-parameter detail, so the baseline of 3 applies.

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 clear verb+resource ("Change job preferences") and adds the defining trait that it is a merge, so only changed fields are sent. It does not explicitly name the sibling set_preferences_from_text, but the merge framing helps distinguish it from a full-replacement tool.

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?

"Used to rank matches and by Autopilot" explains the effect of the settings, which implies context, but there is no explicit when-to-use guidance relative to set_preferences_from_text or get_preferences. An agent must infer that partial edits belong here.

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