run_python

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

Annotations already flag readOnlyHint=false and destructiveHint=true, so the safety profile is covered structurally. The description adds meaningful context beyond that: it returns stdout plus added/changed/removed objects with world sizes so 'silent mistakes show up', warns not to read the add-on source, and explains that session state persists and is wiped by rollback. It never states plainly that the code can mutate or destroy scene data, which the destructive hint implies but the text leaves implicit.

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?

Front-loads the core action and the returned value in the first sentence, then covers routing, documentation policy, and session/paths semantics compactly. Dense but every sentence carries information; no filler.

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 an arbitrary-code-execution tool with no output schema, the description is notably complete: it describes the return payload (stdout plus object diffs with world sizes), the persistence model, and the paths mechanism. Given there is no output schema, the return-value explanation is a real contribution, though failure modes and sandboxing limits go unaddressed.

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 coverage is 0%, so the description must carry all parameter meaning and largely does: `session` keeps variables/functions/imports alive under a name, `reset=true` clears that session, `paths` are folders added to the import path for helper modules. Only `code` is left self-evident. Minor gap: no mention of interaction between paths and sessions or scoping subtleties.

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?

States a specific verb (Run Python) in a specific environment (Blender, listing bpy/bmesh/mathutils/Vector/np/math as preloaded), and explicitly routes away from it for other tasks ('Prefer the other tools for moving, sizing and checking'). An agent can distinguish it from the many modeling siblings like transform_objects or check_mesh without opening a schema.

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?

Gives a concrete routing rule: prefer the dedicated tools for moving, sizing and checking, implying this is the escape hatch for arbitrary logic. It also establishes the session lifecycle (reset=true clears a session; rollback clears all). It lacks a crisp statement of when raw Python is actually the right choice vs. a specialized tool, so it falls short of a full 5.

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