referral_generate_system

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the tool reads or writes, what files it creates, whether it is idempotent, whether it requires an existing project, or what the generated output will look like. The description only vaguely names the deliverable without explaining any behavioral traits.

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 tersely written and has no wasted words, but it is under-specified rather than concisely informative. A good concise description would balance brevity with enough context about the generated system and its key parameter. This one is too sparse to be useful to an agent that must choose and correctly invoke the tool among hundreds of siblings.

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?

The tool sits in a large sibling set, most of which use the same 'generate_<noun>' naming pattern, and it lacks annotations and an output schema. In that context, the description is not nearly complete. The agent cannot tell production behavior, expected input semantics, or how to evaluate success. For a code-generation tool with 2 parameters and no output schema, the description leaves major gaps.

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 50%, with 'directory' documented as 'Project directory'. Adding api_key in the description beyond the bare schema would be valuable. The description does not clarify the role, format, or optionality of 'api_key', nor whether the directory must already exist or whether it will be created. Baseline 3 is fair because the schema does describe the 'directory' parameter, but meaningful parameter semantics are still missing.

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 'Generate referral tracking system' uses a generic verb 'generate' with a noun phrase that likely mirrors the tool name. It does not explain what the system actually does, what components are involved, or how it differs from the closely related sibling 'referral_add_rewards' or 'referral_add_analytics'. The verb 'generate' is common across hundreds of siblings, so the description fails to clearly distinguish this tool.

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?

There is no guidance about when to use this tool versus 'referral_add_rewards', 'referral_add_analytics', or 'inv_generate_system'. The description does not mention required context, prerequisites, or a typical workflow. Context signals show only one required parameter, 'directory', but the description does not state when or why this tool should be invoked.

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