distillery_configure

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 clearly states the tool can read or write, specifies the return shapes for read, write, and error cases, and mentions the `disk_written` boolean in the write return, exposing the side effect of persisting changes. It also notes that `value` 'must satisfy type and range constraints for the given key,' implying validation. This is thorough, honest disclosure with no contradictions.

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 long but every section earns its place: USE WHEN, PARAMS, RETURNS, RELATED. It is front-loaded with the core purpose, then structured so the agent can quickly scan for the information it needs. No redundant filler or restatement of the schema – each line adds new value.

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?

For a tool with 3 parameters, no output schema, and no annotations, this description is encyclopedic. It covers when to use the tool, all valid input combinations, the exact return contracts for success and failure (including error codes), and points to relevant sibling tools. An agent has everything it needs to invoke this tool correctly without further inference.

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?

The schema provides zero descriptions (coverage 0%), so the description must compensate – and it does brilliantly. For `section` it lists the four valid dotted-notation paths. For `key` it gives a per-section breakdown of valid keys. For `value` it clarifies optionality and type constraints. This is more actionable than most descriptions, leaving no ambiguity about parameter meaning or allowed inputs.

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 opens with 'Read or update a runtime configuration value' – a specific verb-resource pair that defines the tool's scope. It then enumerates valid sections and keys, making the exact target clear. Among the sibling tools (store, ingest, classify, watch, etc.), this is the only one that reads/updates runtime config, so it is unambiguously distinguishable.

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 an explicit 'USE WHEN' clause: 'reading current thresholds/settings, or adjusting them at runtime without editing the config file directly.' It also names related tools in the RELATED line: distillery_watch (to manage feed sources) and distillery_status (to review current system state), giving the agent clear guidance on when to prefer those alternatives. This is textbook usage differentiation.

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