start_governed_communication_run

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

Annotations already declare the write (readOnlyHint=false), idempotent (idempotentHint=true), and non-destructive profile. The description adds one genuinely non-obvious behavior—Gmail may follow asynchronously and never inline—which tells the agent not to expect Gmail side effects within this call. However, it omits lifecycle behavior such as what happens to an existing run, so the added context is only partial. No contradiction with 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?

The single sentence is maximally concise and front-loaded with the action and key behavior. However, at roughly ten words it is under-sized for a stateful run-starting tool with three required parameters and a nested request object, crossing from conciseness into under-specification.

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?

An output schema and annotations cover return values and safety, but this is a lifecycle operation with at least three companion governed-communication tools. The description never explains what a governed communication run is, how a source becomes 'approved,' or how this relates to get/cancel/list_governed_communication_run. Ten words are inadequate for this complexity.

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 free-text description is the only possible source of parameter meaning, but it only gestures at 'one approved source' (source_ref). It says nothing about idempotency_key, company_ref, project_ref, the request wrapper, or the gcs_v1_* source format. An agent cannot determine correct values beyond the regex patterns.

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 states an action—'Admit one approved source'—and a behavior note about Gmail, but never explicitly says this tool starts a governed communication run. The core purpose must be inferred from the tool name, and 'approved source' is undefined jargon. It is vague rather than a tautology, so it sits at the minimum viable level.

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?

No guidance is given on when to use start_governed_communication_run versus its counterparts get_governed_communication_run, cancel_governed_communication_run, or list_governed_communication_sources. The only hint—'never inline'—is a negative behavioral constraint, not a selection rule. An agent must guess the appropriate context for invocation.

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