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

With no annotations, the description carries the behavioral burden well: it discloses partial-update semantics, no-launch behavior, immediate application on running processes, and the 5-credit cost when widening the contact segment on a running process. It does not cover permissions/auth or return behavior, so it is strong but not exhaustive.

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 description is compact and front-loads the save purpose before listing settings and caveats. The first phrase ('Outreach window 1 "Save"') is slightly cryptic and the long field list is dense, but every sentence adds useful 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 14-parameter mutation tool with no annotations and no output schema, the description covers the critical behavioral context: partial updates, launch exclusion, immediate application, cost, and dry-run preview. It could be more complete with explicit required search_id usage and return/auth details, but the core is present.

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 only 36%, but the description compensates by naming most parameter groups and adding key semantics: omitted fields keep saved values, dry_run previews, and widening icp_segment on a running process queues more contacts at cost. It still leaves search_id and some individual parameter value details 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 description states a specific save operation for SDR outreach settings and lists the configurable groups: contact segment, channels, sender mode, LinkedIn accounts, time zone, hours, limits, and CRM branch. It also distinguishes this tool from launch behavior by saying 'Never launches' and explaining draft/running process outcomes, so it is separable from sdr_launch_outreach.

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 description makes the main usage boundary clear: this is the Save path and never launches; a new process stays draft, while a running process keeps status and applies changes. It also advises dry_run=true for preview. It stops short of naming sdr_launch_outreach or other sibling alternatives explicitly.

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