bubblyphone-agents

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

Annotations declare destructiveHint and openWorldHint; the description adds critical behavioral context by specifying 'Costs money from your balance' (financial impact) and explaining the AI agent handling in streaming mode. Does not contradict annotations.

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 with zero waste: purpose front-loaded, cost warning second (critical for destructive tool), streaming guidance third. No redundant or filler text.

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 11 parameters and two distinct operational modes (webhook vs streaming), the description covers cost implications and streaming setup but omits webhook mode behavior expectations, transfer functionality details, and success/failure outcomes (though no output schema exists to describe).

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 has 100% description coverage, establishing baseline 3. Description adds minimal semantic value beyond schema, noting the relationship between mode/model/system_prompt for streaming, but does not elaborate on webhook_url behavior, voice selection criteria, or other parameter interactions.

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 specific verb 'Initiate' with clear resource 'outbound call from a BubblyPhone number'. The term 'outbound' and 'make' clearly distinguishes this from siblings like get_call (retrieval), hangup_call (termination), and transfer_call (redirecting existing calls).

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?

Provides clear context for streaming mode usage ('provide model and system_prompt to have an AI agent handle the call') and warns about costs ('Costs money from your balance'). However, lacks explicit differentiation from transfer_call (use this for new calls vs. transfer for existing calls) or when to use webhook vs streaming.

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