Alert text to an alert recipe: turn a sentence like "BTC funding above 0.05%" into the recipe it describes

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds substantial value on top: rule-based, nothing is saved, returns recipe or null, confidence 0..1, and an unresolved list of what was left open or assumed. The guarantee that 'a threshold the text does not state is never invented' is exactly the kind of behavioral contract an agent needs before trusting the output.

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?

Front-loaded with the trigger condition before the return contract, and every clause carries information. It is a single dense paragraph with multiple parentheticals, which slightly taxes scanning, but nothing is 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?

No output schema exists, but the description enumerates the return fields (recipe with name/scope/symbols/conditions/cooldownHours/channels, null, confidence, summary, unresolved), so an agent knows exactly what comes back. For a one-parameter, read-only tool, nothing material is missing.

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 there is only one parameter, so the schema baseline already applies. The description still adds real constraints beyond the schema: input must be English with tickers and is capped at 500 characters. It does not restate the mechanics of the parsed field set beyond naming them, which is fine since the return shape is described.

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+resource (parse alert text into an alert recipe) and immediately grounds it in concrete example sentences. It clearly distinguishes itself from create_alert_recipe and list_alert_recipes in the sibling set by positioning as the parse-only step before creation.

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?

Explicit trigger ('Call this when the user describes an alert in words') with three illustrative phrasings, plus an explicit follow-on action: pass conditions/scope/symbols/channels to create_alert_recipe once the user agrees. The when and the what-next are both stated, leaving no inference needed.

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