wafle_agents_update

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

With no annotations, the description carries the full burden. It adds the useful behavioral note that slug and tenant_id are immutable, and lists fields affected. But it does not disclose key mutation behaviors: whether patch is partial/merge, return values, authorization needs, or status transition rules. This is a moderate gap for an update tool.

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 tight sentences: the first states the action with a useful example list, the second adds a key constraint. No filler, front-loaded, and each sentence earns its place.

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 complex tool with nested objects, no output schema, and empty annotations, the description is under-specified. It fails to explain PATCH merge semantics (e.g., whether tools_allowed is replaced entirely), return structure, error scenarios, or constraints on status/trigger_config values. The agent may struggle to construct a correct patch payload and interpret the response.

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 description coverage is 67% (top-level params: slug and agent_slug have descriptions; patch does not). The description adds semantics for some patch subfields (system_prompt, tools_allowed, guardrails, etc.) but omits others (name, max_turns, temperature, trigger_type, tools_disallowed). It also confusingly references 'tenant_id' which is not an actual parameter, and does not clarify that slug/agent_slug are the immutable identifiers.

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 uses the specific verb 'Patch' with the resource 'existing agent', immediately distinguishing it from create/get/list operations. It lists key editable fields (system_prompt, tools_allowed, guardrails, trigger_config, model, status) and notes that identifiers are immutable, which further clarifies scope.

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 phrase 'Patch an existing agent' clearly implies usage for modifications rather than creation or retrieval. The list of changeable fields provides context for what use cases apply. However, it does not explicitly name alternatives (e.g., 'use wafle_agents_create for new agents') or state when not to use it.

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