Configure a tag (kill type, forwarding, action, appearance, note)

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

With no annotations, the description carries the full burden and does so: it discloses pre-send validation ('values outside these lists are refused before anything is sent'), a hard bridge version requirement (0.36.0), read-back behavior, and a destructive side effect ('Kill Instant turns the other tagged sequences off when one starts'). Batch execution semantics are spelled out in detail: in-order, no retries, unknown outcome halts the remainder, one result line per item.

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 definition is front-loaded with the settable fields, then the semantics, then the batch contract, so structure is sound and every clause carries information. It is dense to the point of being cramped, with stacked parentheticals like '(live, onPC 2.5.1)' and '(the manual: otherwise it works once they have been started)' that slow parsing.

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 10-parameter mutation tool with no annotations and no output schema, the description covers side effects, validation, ordering, failure behavior and the shape of the return value (one line per item, detail for steps). It leaves stop_on_failure undescribed and its claim that 'an unknown outcome stops the rest' sits uneasily beside the schema's stop_on_failure default of false, leaving the agent to reconcile the two.

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 100%, so the baseline is 3, but the description adds real meaning: forward_commands is explained concretely ('whether Go+ Tag n / Off Tag n reach the tagged objects'), appearance null clears, and the default-vs-override rule that an item's own fields win over the batch-level arguments. stop_on_failure and verify are only implicitly touched ('read each one back').

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 opens with a specific verb plus resource and enumerates exactly what gets set: type, forward commands, pool action, appearance and note, followed by read-back. An agent can distinguish this from gma3_store_tag or gma3_delete_tag on the verb alone, though no sibling is named 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?

It gives a concrete condition for the single-object form versus the batch form ('give the list instead of the single object's fields') and states that the type must be set before the sequences run. It does not explicitly route the agent to gma3_store_tag for creation or state when this tool is the wrong choice.

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