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

Goes well past the annotations: it discloses that people without an email are skipped, that findEmails triggers lookups bounded by maxEmailLookups and a daily limit, that LinkedIn enrollment uses the paced engine against an approved sequence, that campaign steps/schedule/mailboxes can be configured in the same call, and crucially that nothing is launched or sent here. This is exactly the mutation-effect context the annotations do not carry.

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?

Front-loaded with the selection rule and channel split, and dense with substance rather than filler. It is a single long paragraph that would benefit from tighter segmentation, but each clause earns its place for a 16-parameter tool.

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 highly complex 16-param, no-output-schema tool, the description covers selection, both channel modes, and the no-send caveat. It omits what the call returns (e.g. enrolled/skipped counts) and error/failure conditions, which are the only meaningful remaining gaps.

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 only 6%, so the description must compensate, and it does: it explains competitor/playId/candidateIds selection, notYetEnrolled's skip semantics, campaignId vs a new campaignName draft, the steps fields (plain text, {{firstName}} {{company}} {{title}} placeholders, delayDays), schedule, mailboxIds/allMailboxes, dailyLimit, sequenceId, and findEmails/maxEmailLookups. Nearly every non-trivial parameter gains meaning beyond the bare 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?

States a specific verb ('Pick people ... and reach them'), the exact resource pool (the account universe), the selection axes (competitor name, playId, or candidateIds), and the two distinct behaviors keyed on channel. An agent can tell this apart from reach_post_engagers or add_to_sequence purely from the description.

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?

Gives clear operating context: exactly one channel per call, channel=email routes to an email campaign while channel=linkedin enrolls into an active approved sequence. It does not, however, name sibling alternatives or state when to prefer this tool over add_to_sequence/reach_post_engagers, so selection between siblings is left to inference.

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