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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds materially new behavior: Admin/Owner permission needed for scoring, history mode capped at five exact IDs and limit five with 30 UTC sampled points, current-only scoring supporting the ordinary 50-employee page, and the crucial caveat that insight filters narrow evidence rather than Employee selection. It also clarifies the return shape (one summary per Employee with pagination, not individual observations or Learner Sessions), which goes well beyond the annotations.

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?

Content is front-loaded: purpose and selection mechanics come before the summary-shape details. It is a single dense paragraph of many sentences, though, and a short bulleted split between selection rules, output contents, and constraints would improve scanability without losing information.

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 deeply nested, five-parameter tool with high complexity, the description covers selection semantics, per-section behavior, permission requirements, pagination/history limits, and what the response contains. Since an output schema exists, it correctly stops short of exhaustively documenting return fields while still flagging the summary-level granularity.

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 100%, so the baseline would be 3; the description earns an extra point by adding semantics not present in the schema, notably that an empty object requests a section without evidence filters, that insight filters affect summarized evidence rather than selection, and the history-mode ID/limit/point caps. It still leaves some nested details (e.g. how `match` interacts with `ids` plus `query`) to the schema.

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 opening sentence names a specific verb (Find/return) plus resource (Employees within one Organization) plus the exact payload (Simulation, Training, canonical scoring summaries). The description also explicitly carves out scope against alternatives with "Does not discover, filter, or rank Employees by score," so an agent can distinguish it from sibling tools like search_employee_activity without opening a schema.

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?

It gives concrete when-to-use cases (inspect one Employee, compare selected Employees, review a Group or Dynamic Group) and a how-to-select rule (by IDs or literal name/email, omit filters to browse). The main gap is that it never names a concrete sibling tool as the alternative, stating only the negative constraint that it does not rank or discover by score.

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