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

Annotations already declare a non-read, non-destructive, idempotent mutation, so the bar is lower. The description still contributes real value by stating the partial-update contract ("Only the fields given change; every other preference is kept"), which is consistent with idempotentHint and tells the agent it need not resend a full preference set. It omits auth requirements and what the response contains.

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: the scope and field list come first, and the partial-update rule follows as the key caveat. No filler, no restatement of the title.

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 7-param, all-optional mutation with no output schema, the description covers scope and the merge semantics that matter most for correct invocation. The remaining gap is the null-vs-omitted ambiguity in nullable params, which an agent could get wrong when trying to clear a preference.

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 0% and there are 7 optional params, so the description carries full burden — it does list every updatable field (job types, experience levels, remote work, categories, minimum salary, relocation, availability), mapping 1:1 to the schema. It adds no depth beyond name-mapping, leaving unclear whether passing explicit null clears a field or is treated as "unchanged".

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 gives a specific verb+resource ("Change the caller's job preferences") and enumerates the exact facets it covers, so an agent can tell it apart from read tools like get_profile. It never mentions the nearby sibling update_profile, leaving the preference-vs-profile boundary implicit.

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 only implied by "Change the caller's job preferences" — there is no explicit when-to-use, when-not-to-use, or "use update_profile instead" routing despite update_profile being a close sibling. The partial-update sentence helps clarify a common update scenario but is behavioral, not a selection guideline.

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