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

Discloses validation behavior (requires APPROVED template, rejects unmapped placeholders), the exact error code and its metadata, side effects (sends to every contact), and return values. Goes far beyond the annotations (which only indicate destructive and open-world) by explaining failure modes and fixes.

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?

Long but every sentence adds critical value. Front-loaded with the core action, then covers prerequisites, error handling, and alternatives in a logical order. No redundancy or filler.

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?

Given the complexity (error codes, prerequisites, return values, alternatives), the description is exhaustive. It explains what the tool does, when to use it, how to handle failures, and what it returns, all within a single coherent definition.

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?

Compensates for the 50% schema coverage by explaining the effect of scheduled_at (omit to send now) and timezone_mode (account vs contact). Also implicitly clarifies segment_id and template_id via the resource description and ties template_id to validation behavior.

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 (send or schedule) and a precise resource (broadcast: one approved template to every contact in a segment). Clearly distinguishes from siblings like preview_broadcast and set_template_variables by name and purpose.

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 instructs to call preview_broadcast FIRST, to call get_started for new workspaces, and names alternatives for specific errors (set_template_variables for unmapped placeholders, get_subscribe_link for billing issues). Provides clear when-to-use and when-not-to-use guidance.

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