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

Annotations already signal destructive mutation, read/write behavior, and non-idempotence. The description adds behavioral disclosures beyond the annotations: locked displays are skipped with reasons, all=true means 'every accessible display', and dry_run previews without sending. It also states the auth requirement 'Requires content scope'.

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 compact sentences front-load the core purpose and then layer targeting, preview, and constraints. No filler or redundant restatement of the schema.

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 11-parameter broadcast tool with an output schema present, the description covers auth scope, targeting modes, locked-display failure behavior, and alternative routing. It stops short of stating explicit conflict rules between targeting parameters, but the 'or' phrasing and full schema coverage make the remaining ambiguity minor.

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?

While the schema covers 100% of parameters, the description adds grouping semantics: it identifies the three mutually exclusive targeting strategies ('explicit display_ids, all=true... or include_category_ids'), explains include_descendants as subcategory expansion, and positions dry_run as a preview option across all modes. This synthesis is value beyond the per-parameter schema text.

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 opening sentence 'Sends HTML to many displays at once' states a specific verb plus resource and scope. It distinguishes itself from send_html with 'For a single display use send_html', and names the three targeting modes. This leaves no ambiguity about what the tool is for.

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 explicitly tells the agent when to prefer the sibling send_html ('For a single display') and when broadcast_content is appropriate (explicit display_ids, all=true, or include_category_ids). It also covers preview with dry_run and subcategory expansion with include_descendants, giving concrete selection context.

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