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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower, and the description adds a useful caveat that compensation data is sensitive. It does not disclose volume or pagination behavior for what is clearly a multi-collection historical response, nor whether terminated/inactive records are included.

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?

One dense sentence, front-loaded with the verb and resource, followed by a compact colon list of contents and a single high-value caution. No redundant restatement of the title or annotations.

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-parameter read with no output schema, enumerating the returned record categories plus the compensation-sensitivity warning covers what an agent needs to call it and interpret the result. Minor gaps remain around historical range and multi-collection response shape.

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 100% and the schema already documents that employee_id comes from talenthr_list_employees, so the description's silence on the parameter is acceptable. It adds no format or sourcing detail beyond the schema, making the baseline 3 appropriate.

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 specific verb ('Get') and a well-defined resource ('one employee's job information'), then enumerates the record types returned: employment status history, manager records, job records, compensation, benefits. This enumeration effectively distinguishes it from generic sibling reads like talenthr_get_employee, though no sibling is named explicitly.

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 clause 'only fetch it when the user asked' is real usage guidance for the sensitive compensation portion, but it is a data-handling constraint rather than a routing rule. It never says when to prefer this tool over talenthr_get_employee or talenthr_get_employee_benefits, which overlap with the returned data.

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