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

Annotations already cover the safety profile (readOnly, non-destructive), but the description adds genuinely non-obvious behavior: personal data is excluded by default, gated behind include_personal, and payroll/bank/tax/insurance are never returned regardless. That privacy scoping is real behavioral context an agent cannot get from structured fields, though failure modes for bad ids are unmentioned.

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?

The scope and the default-vs-personal distinction are front-loaded and every clause about field content earns its place. The trailing "GraphQL query user." is an implementation leak with little decision value and is the only real waste.

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?

There is no output schema, so the description's field-group inventory carries the full burden of describing what comes back, and it does so at two levels (default vs include_personal) plus an explicit exclusion list. Nothing an agent needs to call this correctly is missing.

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%, so baseline is 3, but the description expands include_personal far beyond the schema's abbreviated note by listing the exact personal data classes it unlocks. This goes past restatement and helps an agent judge whether to set the flag.

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?

"One employee by id" states a specific verb and resource and immediately scopes it to single-record retrieval, distinguishing it from list_users. The enumeration of returned field groups makes the tool's identity concrete rather than tautological.

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 singular "one employee by id" implies you need an id and that list_users is the alternative for enumeration, but no sibling is named and no when-not-to-use condition is given. Usage is inferable rather than explicit.

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