ai_bullet

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the use of a 'configured free LLM' and input restrictions, but does not disclose traits like idempotency, failure modes, or rate limits, which are gaps for a text-processing tool.

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?

The description is extremely concise: two sentences with zero fluff. The first sentence covers purpose and mechanism, the second adds necessary constraints. Every word earns its place.

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 low complexity (1 parameter, no output schema, no annotations), the description is fairly complete. It explains input format, output format (markdown bullet list), and constraints. However, it lacks details on edge cases like large text handling or bullet nesting, leaving minor gaps.

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% and the parameter description is adequate, but the tool description adds value by explicitly restricting input to 'Plain prose only — no code, secrets, or file paths', which goes beyond the schema's 'Plain text' description.

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 description states the verb 'Extract key points', the resource 'plain text', and the output format 'markdown bullet list'. It also specifies constraints ('using a configured free LLM', 'Plain prose only'), clearly distinguishing from siblings like ai_summarize or ai_outline.

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 provides clear usage context by stating that the tool is for plain prose and explicitly excluding code, secrets, or file paths. However, it does not name alternative siblings when those constraints are violated, leaving some guidance implicit.

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