propose_factories

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

With no annotations, the description carries the full burden and does well: it discloses input signals, validation metrics (precision/recall), and a behavioral characteristic ('never merges two factories, only splits one'). It does not describe return format or side effects, but the tool appears read-only by design.

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?

Three concise paragraphs with the purpose front-loaded. The validation statistics are slightly tangential but add credibility. No unnecessary words.

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?

Despite strong behavioral and usage context, the output format (structure of a proposed factory) is not described, and save/world parameters are not elaborated. With no output schema, this is a notable gap for an agent to invoke the tool and interpret results correctly.

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?

Only unnamed_only is explained with a practical use case, adding value beyond the schema. The other parameters (save, world, limit, max_span_m) are left to the schema, which covers only 40% of parameters. The description partially compensates but not fully.

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 clearly states the tool's function: producing a coherence score over signals and agglomerating them into proposed factories. It differentiates itself from siblings by explicitly directing to 'name_factory' for naming and describing the 'unnamed_only' use case.

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?

Clear context is provided: use this to discover factory groupings and identify unnamed factories. However, it does not explicitly compare against alternatives like factory_map or list_factories, nor 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.