confirm_reliance

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

Discloses important refusal behavior and that it never silently credits. With no annotations, description carries full burden; could mention idempotency or side effects, but sufficient.

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?

Two concise sentences front-loading purpose and conditions. Zero wasted words.

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?

With output schema present, return values don't need elaboration. Description covers gate condition and state transition. Slight gap: doesn't explicitly state it only works on draft edges, but context implies.

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 covers 2 of 3 params with descriptions. Description does not add new meaning to params beyond schema. Baseline 3 is appropriate.

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?

Clear verb 'promote' and specific resource 'draft reliance edge' with gate context. Distinguishes from similar tools like 'create_reliance' and 'delete_reliance'.

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 states refusal conditions (LLM validation must be 'valid', not 'partial' or mode mismatch). Good context for when to use, though no alternative tools named.

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