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 genuinely useful trait that results carry citations, but says nothing about ordering, coverage window, or what a timeline entry looks like beyond the output schema's implication.

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. Efficient, though the brevity is part of the reason other dimensions are thin rather than a virtue in itself.

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?

With four optional parameters at 0% schema documentation and a boolean (includeEducation) whose effect is never stated, the definition is too sparse for an agent to call confidently. The output schema covers return shape, but nothing explains default limit=10/max 20 or what query filtering actually matches.

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%, so the description must compensate for all four parameters. It only gestures at two of them (query, company), never explaining what query matches (role? company? skill?) or what the difference between query and company is, and it omits limit and includeEducation entirely.

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?

"Returns citation-backed career milestones" names a specific verb and resource, and "citation-backed" distinguishes the output from plain career data. It does not, however, differentiate itself from the many career siblings (get_career_education, get_career_role_detail, get_career_certificates), so the agent must infer that this is a chronological milestone list.

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 phrase "optional query/company filtering" hints at use cases but never states when to choose this over get_career_role_detail or get_career_education. No when-not conditions or alternatives are given anywhere in the one-sentence description.

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