Set an object property

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

With no annotations at all, the description carries the full burden and does so: it discloses that the show file is modified, that property plus the object's Lock and SystemLocked are read before writing, that the console silently keeps the old value on a rejected write, and it enumerates verified / failed / unverified outcomes including the recovery action (Unlock, set, Lock again). It also explains that unverified is not an error and points to the typed tool that can check the read-back, which is exactly the context an agent needs to interpret a result.

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 identification and example content is front-loaded, which is good, but the remainder is a run-on block of long comma-chained sentences with no separation between the lock behavior and the verification taxonomy. Every fact earns its place, yet the lack of structure makes the verified/failed/unverified distinctions harder to extract than they need to be.

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 three-parameter mutation tool with no annotations and no output schema, the definition covers the important ground: what is mutated, what is returned (verification state, read-back, and a hint naming the checking tool), and how failures present. The main remaining gap is procedural guidance on choosing this tool over the other set/store siblings.

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 only 33% – only 'ref' is documented – so the description must compensate, and it does for the two undocumented parameters. It explains that 'property' takes field names like 'Name', 'Tracking' or 'TrigTime' and that 'value' is passed as text the way it would be typed in the editor ('Yes', 'No', '2.5', 'Follow'), which tells the agent a stringified value is acceptable despite the union type in the schema.

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 verb and resource: setting a property of a show object through the Lua Set() API, and it grounds that with concrete example pairs ('Sequence 1' / 'Name', 'Sequence 1 Cue 2' / 'TrigTime'). That is enough for an agent to tell it apart from narrower siblings such as gma3_set_attribute or gma3_set_color, though it never names those siblings explicitly.

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 context is implied rather than stated: it directs the agent to gma3_get_object, gma3_macros / gma3_edit_macro_line and gma3_tags for verifying values it cannot confirm. There is no explicit 'use this instead of X when Y' routing against the many other set/store tools in the sibling list, leaving the agent to infer when the generic Set() path is preferred over gma3_command or gma3_lua.

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