sb_alert_dismiss

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

With no annotations, the description fully discloses behavior: default policy, settle time, loop mechanics, return values (cleared/remaining/rounds/needsRetry), retry logic, and a warning against parallel tap+dismiss. This is rich and transparent.

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 concise and front-loaded with the main action, but uses dense shorthand (e.g., '~300ms settle', 'trust cleared; empty → cleared:true rounds:0') that could be clearer. Could benefit from slight restructuring for readability.

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 high schema coverage and no output schema, the description covers parameters, behavior, return values, and caveats. Mostly complete, but the settle time behavior and 'trust cleared' concept could be elaborated for full clarity.

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%, but the description adds significant extra meaning beyond the schema: explains how 'all' controls single vs stacked mode, default values for policy and maxRounds, and settling mechanics. This adds substantial value for correct invocation.

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 clearly states 'Dismiss SB alert' and distinguishes between single (all=false) and stacked (all=true) modes. It uses specific verbs and resources, and the purpose is distinct from sibling tools like sb_alert_list or sb_alert_trigger.

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 explicit context on when to use all=false vs all=true, and includes instructions on retry behavior and a prohibition against parallel actions. Does not compare to alternative tools, but siblings are different actions so this is acceptable.

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