set_word_automatic_tool

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

With no annotations, the description carries the full burden and does substantial work: it discloses that the call does NOT itself change 'suppressed', that a reconcile is needed, that a stale-word refusal is possible via expected_text, and that a word_source_required refusal can occur. It does not cover permission/auth needs or idempotency, so it falls just short of fully transparent.

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 core action and its sibling relationship are front-loaded in the first sentence, and the sequencing/refusal details follow compactly. The '``suppressed`` waits for the next reconcile (#824)' aside and the tracked issue number add internal jargon noise that an agent cannot act on, keeping it short of a 5.

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 high-complexity, stateful mutation tool with an output schema (so return values needn't be described), the description covers preconditions, the required follow-up call, and both refusal paths. The main residual gap is project_path scope/validation, which is neither in the schema nor the description.

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%, so the description must compensate, and it does for the non-obvious params: source_id is explained as naming the recording whose words word_index counts, including the multi-take requirement and the word_source_required refusal; expected_text is explained as the read-word guard; and word_index semantics are pinned by 'TOOL_TIMEBASE: source'. track_id and project_path are left unexplained but are self-evident.

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+resource ('Clear one word's suppression lock') and immediately explains the inverse relationship to set_word_suppressed_tool ('A word set directly by set_word_suppressed_tool ... stays audibility_locked until this call'). An agent can distinguish this from set_word_suppressed_tool and apply_low_audibility_suppression_tool without opening any 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?

It states exactly which upstream operations create the condition this tool resolves (set_word_suppressed_tool, explicit-list suppress-bleed/low-audibility apply, Studio's Suppress toggle) and prescribes the required follow-up ('run reconcile_transcript_tool after to get the computed target'). It also explains when to pass vs omit expected_text. 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.