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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds exactly the context that matters: emails are sent on the schedule, already-sent emails cannot be recalled, and pause_campaign is the only lever over the rest. That is concrete irreversibility detail beyond the annotation flags.

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?

A single dense sentence that front-loads the action, then the consequence, then the escape hatch. Every clause earns its place; only the parenthetical placement slightly interrupts the flow.

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 one-parameter mutation with no output schema and rich annotations, the description covers the key risks (irreversibility, preconditions, stopping mechanism). It falls short only on sibling disambiguation against resume_campaign, which is the main remaining ambiguity.

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?

Only one parameter (id) with 100% schema description coverage, so the schema fully documents it. The description's lead/sequence requirement describes campaign state rather than the id argument, adding no syntax or format meaning beyond 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?

States a specific verb and resource ("Start sending a draft campaign") and clarifies the effect is real emails going to leads. Implicitly differentiates from resume_campaign by scoping to a draft, but never names resume_campaign as the sibling that handles paused campaigns, so an agent must infer that distinction.

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 a concrete precondition ("Needs at least one lead and a sequence") and points to pause_campaign as the way to stop remaining sends. However it offers no explicit guidance on when to use this versus resume_campaign, leaving the draft-vs-paused choice to inference.

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