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

Annotations already flag destructive/openWorld/non-idempotent, but the description adds the consequences an agent actually needs: real emails to all matching contacts, irreversible, immediate return with status 'sending', and the warm_send pacing behavior that changes delivery timing up to 24 hours. This is behavior 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?

Five short sentences, each load-bearing: purpose, irreversibility warning, consent gate, precondition, pacing nuance, and return/monitor behavior. The critical warning is front-loaded right after the purpose.

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?

No output schema exists, but the description compensates by stating the immediate return value ('sending') and pointing to meisa_get_broadcast for progress. Combined with the precondition and consent gate, an agent has everything needed to call this correctly and safely.

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% for the single broadcast_id parameter, so the baseline is 3. The description adds a real constraint on the parameter's valid value (it must reference a broadcast in 'draft' status) and a sibling tool to inspect it, which is meaning the schema does not carry.

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 ('Queue a draft Meisa broadcast') plus the scope 'for immediate delivery,' which separates it from meisa_schedule_broadcast and meisa_test_send_broadcast without needing to open their schemas.

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 an explicit precondition ('broadcast must be in draft status'), an explicit consent gate ('only call this after the user has explicitly confirmed'), and names meisa_get_broadcast as the way to verify state. When-to-use and how-to-verify are both covered.

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