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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered, but the description adds non-obvious behavior: action='audit' blocks and waits for the run before returning its report, and action='get' exposes the monitor's editable configuration. It also records a data-source constraint (GAWA supports metrics only) that is not in any structured field. It stops short of describing failure modes or how long the audit wait can take.

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?

Purpose and monitor-vs-audit distinction are front-loaded, followed by a compact operation list and then the inference fallback, which is a sensible ordering for a dispatcher-style tool. The prose is dense but nearly every clause carries operational meaning; the long parenthetical action list is slightly heavy to parse but not padded.

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 five-parameter, zero-required dispatcher with an output schema, the description covers what an agent needs: what each action does, which parameters each action consumes, how action is inferred when omitted, where run_token originates, and the constraint on id ids. Return-value shape is legitimately left to the output schema.

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 each parameter description already states which action consumes it, so the description largely restates the schema on this axis. The added value is modest but real: the inference rule that omitting action derives it from the other fields, and the reminder that run_token is not a monitor run token, both help avoid misuse. Baseline 3 is appropriate given the schema does the heavy lifting.

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 pairs a specific verb (read) with two distinct resources and defines each: monitors are "scheduled checks: metrics, page_check and naming_convention" and an audit is "a one-off review of one AW or FA account." It then enumerates the four operations (list/get/schema/audit) with their arguments, so an agent can distinguish it from manage_audits_and_monitors and field_discovery without opening any 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?

Each operation is scoped with the condition that selects it (monitor_id implies get, run_token implies schema/audit, otherwise list), and the description routes the agent to the sibling that produces run_token: manage_audits_and_monitors(action='audit'). It also gives an explicit exclusion — action='list' takes no arguments — and warns that metric/dimension ids must come from field_discovery rather than being guessed.

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