bp_find_unused_variables

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

No annotations are provided, so the description carries the burden. It explains the tool reports 'possibly_unused' vs 'unused' based on safe_mode, which adds important behavior not inferable from the schema. However, it doesn't mention whether the tool has side effects (e.g., modifying the blueprint) or performance impact, but likely it's read-only. The description covers the key behavioral nuance but could be more explicit about read-only nature.

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 fairly concise, with a clear opening line, an important note, and then args/returns sections. The KB link and example add some length but are useful. It's well-structured with headers, though the args/returns sections could be considered verbose. It's appropriately detailed for a tool with two parameters.

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?

There is an output schema, so return values are partially self-explanatory, but the description additionally lists the outputs (unused_variables[], all_variables[], variables_checked), which is helpful. It also provides an example call and a KB reference for deeper guidance. The only missing piece could be error handling or edge cases (e.g., what if no variables are found), but overall it's complete for an agent to call it 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?

The schema has zero description coverage, so the description must explain both parameters. It gives full arg docstrings: blueprint_path as full asset path or plain name, and safe_mode with its boolean meaning and default. This goes beyond the schema's field 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 clearly states the tool finds Blueprint variables declared but not referenced in any graph. It specifies the action, resource, and the nuance between 'unused' and 'possibly_unused'. This distinguishes it from sibling tools like bp_find_disconnected_pins or bp_find_orphaned_nodes.

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 explicitly warns about instance-editable variables and provides a safe_mode parameter to control this behavior. It gives a clear rule: use safe_mode=True to avoid false positives. This is practical guidance for when to use the tool and how to adjust its behavior.

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