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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds the useful detail that data comes from first-party employment history, but says nothing about what happens when only one role is supplied, what detailLevel changes in the output, or any coverage/fallback behavior.

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?

A single front-loaded sentence with no filler; the object of the comparison and the data source are stated immediately. It is efficient, though its brevity contributes to the semantic gaps noted elsewhere.

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?

An output schema exists, so return shape needn't be described, but for a six-parameter tool with zero schema documentation the description should explain how left/right roles and companies combine, what 'query' does, and what each detailLevel yields. None of that is present, leaving invocation ambiguous despite annotated safety.

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 0% across six parameters, so the description carries the full burden. It implies a left/right pairing of roles and companies but never explains the free-text 'query' parameter, the summary/detailed/full detailLevel enum, or the fact that all parameters are optional (required: 0), which materially changes how the tool should be invoked.

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 names a specific verb (returns a side-by-side comparison) and a specific resource (two career roles/companies) backed by a stated data source (first-party employment history). It implicitly contrasts with get_career_role_detail's single-role view, but never names the sibling, so differentiation must be inferred.

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?

There is no guidance on when to use this instead of get_career_role_detail, get_career_timeline, or search_first_party_context, and no note on prerequisites such as whether both roles must exist or whether companies are optional. The only hint of usage is the word 'comparison' itself, which leaves the agent to guess.

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