vw2d_edit

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

Annotations only say readOnly=false/destructive=false; the description goes much further, disclosing the in-place vs rebuild fork, that uuid is preserved on in-place edits and a new uuid is returned on rebuild, that class/attributes/name/group/stacking survive a rebuild, and that the operation is one undo step. That is exactly the behavioral context an agent needs before calling a mutation tool.

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 mutation behavior is front-loaded in the first sentence and the remaining clauses are all load-bearing, with zero filler. Dense but readable, sized appropriately for an 8-parameter geometry edit.

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 destructive-capable geometry rewrite with no output schema and no schema descriptions, the description covers the essential contract (input modes, identity/rebuild semantics, undo). The gaps are the unexplained unit, relative, and closed parameters, which an agent must guess at from the schema defaults alone.

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% across 8 parameters, so the description has to carry the load. It does well on the three geometry inputs (points as corner pairs, path matching vw2d_draw, vertices as [x, y, type, radius] from vw2d_read) and on holes, but says nothing about uuid, unit (which has an enum), closed, or relative, leaving half the parameters undocumented anywhere.

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?

Opens with a specific verb and resource: 'Replace the outline of a polygon/polyline/rect exactly.' An agent can tell this mutates an existing object's geometry rather than creating one. It never names a sibling such as vw2d_draw or vw2d_transform to sharpen the boundary, so it stops short of a 5.

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?

'Give one of: points, path or raw vertices' explains the mutually exclusive input modes and points at vw2d_draw paths and vw2d_read output as the canonical formats, which strongly implies edit-existing vs draw-new. But there is no explicit when-to-use statement and no exclusions (e.g. why choose this over vw2d_draw or vw2d_transform).

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