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

With no annotations, the description must carry the full behavioral burden. It signals a non-mutating observation and explicitly discloses the limitation that referee checks are hidden, which is genuinely valuable, but it says nothing about state prerequisites (must the forge already be entered?), error behavior, or cost of the call.

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 short sentences, front-loaded with what the agent will see before the caveats. Every sentence carries information: the output contents, the hidden-checks boundary, and the frame behavior. The opening metaphor 'Look at your work' is slightly soft but immediately grounded by concrete output detail.

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 two-parameter inspection tool with no output schema, the description does the essential work of describing the return value (bounding boxes and text silhouettes) and the animated-trial variation. Its main gap is not stating any precondition on the forge state before observation.

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 100%: forge_handle is documented as coming from enter_forge and frame already spells out 0 vs. 1..max_frames. The description's 'frame chooses the pose to look at' merely restates that, adding no new syntax or edge-case meaning, so the baseline 3 applies.

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 states a specific inspection action and enumerates exactly what is returned: every part's world bounding box plus front and side silhouettes rendered as text. Among the forge_* siblings (add, edit, remove, keyframe, seal) this is unambiguously the read/observe tool, though no sibling is named explicitly to reinforce the contrast.

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?

Usage is implied (look at your work to verify the build) rather than stated, and there is no guidance like 'call after forge_add' or 'call before seal_forge'. It does add one useful scoping rule — it does not reveal the referee's checks — which steers the agent away from an expectation it might otherwise have, plus a conditional note for animated trials.

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