Shape edit node

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

Annotations only say readOnly=false, destructive=false, idempotent=false, openWorld=false; the description goes far beyond that by disclosing the document-level singleton constraint (assigning fire faces to another node silently clears the previous node's), the viewport rendering of fire faces (red hatching), the downstream wiring to a FIRE SURF + RAMP_Q/&REAC on shape_export_obst, and the no-op/queries-instead behavior when plan_confirmed is absent. The per-key merge semantics ('unspecified keys keep their previous value') are also behavior the annotations cannot express.

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?

It is long and formatted as one dense block, but it is front-loaded with the operation list and then uses caps-labelled clauses ('ONE FIRE OBST PER DOCUMENT', 'PLAN FIRST') to make the critical rules scannable. Some of the fire_* bullet text restates schema descriptions, which is minor waste for a 15-parameter tool.

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 15-parameter, no-output-schema, domain-specific mutation tool the description covers the workflow, the singleton side effect, the flatness gating and the fire-property merge rules, which is nearly everything needed to call it correctly. It never tells the caller what a normal successful call returns or how to obtain the node id, but the plan_confirmed fallback behavior is explicitly described.

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 67% and the five uncovered params (id, name, color, surf_id, visible) carry obvious meanings, so the baseline is not low. The description still adds real meaning beyond the schema: the exact 6-boolean ordering [-X,+X,-Y,+Y,-Z,+Z], face-name strings and 'bottom'/'top' aliases, [] to clear, °C for fire_tmp_front, the [t_seconds, fraction] shape of ramp points, and the individual-key merge rule that the schema never states.

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 opening sentence gives a specific verb set and resource: 'rename / show-hide / assign FDS SURF / set color / mark fire faces + fire properties of a node.' An agent can tell this is the node-level editor in the Shape Studio family (as opposed to shape_add_* creators or shape_export_* writers) without opening the 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?

The 'PLAN FIRST' block gives an explicit precondition and workflow: setting fire_faces without plan_confirmed changes nothing and returns a flatness analysis, so the agent must discuss flat face/HRRPUA/RAMP with the user and re-call with plan_confirmed=true. What is missing is routing against the close sibling shape_set_params, which is never mentioned, so a caller cannot tell which of the two to prefer for plain parameter edits.

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