secret_create

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

Discloses critical behavioral traits: write-once semantics, payload never readable via API, inability to change, provenance labeling, and the data size/empty when driver set constraints. Annotations only state readOnlyHint=false and destructiveHint=false; the description adds substantial safety-critical context without contradicting annotations.

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?

Well-structured: opening one-liner, then behavioral notes in tight prose, followed by a clean args list. Every sentence carries meaningful information without fluff. Front-loaded with purpose and key constraints.

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 4-param tool with nested objects and no output schema, this description covers: purpose, prerequisites, alternatives, behavior, constraints, parameter meanings, and return value. The explicit note that returns 'never the payload' prevents dangerous assumptions. Missing output schema is compensated by return description.

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?

With 0% schema description coverage, the description fully compensates: name (unique within swarm), data (max 500 KB, must be empty if driver set), labels (labels to set), driver (optional config for external store). It adds semantics and constraints beyond the bare schema types.

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 'Create a swarm secret' – a specific verb and resource, clearly distinguishing it from config_create, volume_create, and other create tools. It explicitly contrasts with config_create for non-sensitive data, removing ambiguity.

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?

It states the prerequisite ('requires a swarm manager'), provides an explicit alternative for non-sensitive data ('use config_create instead'), and offers rotation workflow guidance ('create a new secret and update the consuming services'). This goes beyond any sibling differentiation.

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