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

The annotations declare destructiveHint=true, implying potentially destructive updates. The description directly contradicts this by stating the broadcast is created as a DRAFT and 'nothing goes out until send_broadcast', so the tool itself has no destructive effect. This is an annotation contradiction.

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?

Three sentences, front-loaded with purpose, then draft status, then network limitations. Every sentence adds necessary context without repetition.

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 an 8-parameter tool with no output schema, the description covers purpose, draft behavior, network constraints, and the next step (send_broadcast). It leaves individual parameter details to the rich schema, which is reasonable, but does not reconcile the contradictory destructiveHint annotation.

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 88%, so the schema already documents most parameters in detail. The description adds network policy constraints (Instagram/Facebook disallowed, WhatsApp template required), but these are usage-level rather than per-parameter semantics. Baseline 3 applies.

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: 'Create a mass message to the CRM contacts of one account.' It also distinguishes the output as a draft, setting it apart from send_broadcast and other creation tools.

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?

Explicitly says nothing goes out until send_broadcast, naming the alternative. It also gives network-specific when-not conditions: Instagram and Facebook do not allow broadcasts, and WhatsApp requires an approved template.

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