modify_entities

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

Annotations already flag it as a destructive, non-read-only, idempotent write; the description builds on this with write-time validation behavior — unknown paths or missing components fail immediately with an error listing the entity's valid paths, enabling one-shot self-correction — plus the return shape (post-edit entity summaries) and per-edit targeting semantics. No contradiction with annotations; the idempotentHint is consistent with set/unset semantics.

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 long but front-loaded: the operative verb+resource lands in the first clause, followed by path grammar, then failure behavior, then exclusions. Every sentence carries semantic weight, though some phrasing ('so you can fix it in one shot instead of retrying blind') is mildly editorial and the example list could be trimmed without loss.

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 write tool with one complex parameter, a low-coverage schema, and no output schema, the description covers virtually everything: valid values, grammar, units, prerequisites, failure mode, return shape, and sibling routing. The one remaining gap is batch semantics — if an edits array contains several entries and a later edit fails, it is not stated whether earlier edits already committed or the whole batch rolled back.

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 minimal, and the description compensates fully: it enumerates valid top-level paths with units and coordinate space ([x,y,z] local for position, euler degrees for rotation), gives the component-path grammar with four concrete examples, states the has-component prerequisite, and clarifies that each edit targets exactly one entity id + one path. This goes well beyond the schema's terse 'Property path in dot notation.'

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+resource pair — 'Set or unset properties on existing entities by dot-notation path' — and then enumerates the exact valid path space (top-level: name, enabled, position, rotation, scale, tags; component: components.<type>.<prop>). The scope is crisp: this tool mutates properties on entities that already exist, which visibly separates it from create_entities, add_components/remove_components, and modify_scene_settings.

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?

Provides an explicit 'When NOT to use' section naming three alternatives with the exact condition that routes to each: create_entities for creation, add_components/remove_components for component lifecycle, and modify_scene_settings for scene-wide changes. It also gives positive routing guidance ('add it with add_components first') for the component-prerequisite case. Nothing is left to inference.

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