apply_transcript_cleanup_tool

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

With no annotations, the description carries the full burden. It usefully discloses that the whole batch lands in one undoable history step, which is real behavioral context. However, it says nothing about permission requirements, whether indices must be valid/contiguous, error behavior on partial failure, or what the response contains.

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?

Two compact blocks, zero filler, with the operation and its undo property front-loaded before the payload shape. Every element earns its place.

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?

An output schema exists so return values need no explanation, and the corrections payload is documented. But for a mutation tool with no annotations and two undocumented parameters (track_id, project_path), the definition omits usage routing and failure/validation semantics that an agent would need to call it correctly.

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% and 'corrections' is an open object with additionalProperties:true, so the description's inline shape for words ({word_index, text}) and phrases ({start_word_index, end_word_index, text}) is the only documentation of the hardest parameter. It does not explain track_id or project_path, but the critical nested structure is covered.

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?

States a specific verb and resource ('batch word + phrase fixes') and adds a distinguishing trait ('one undoable history step') that separates it from single-fix siblings like correct_transcript_tool. It stops short of naming those siblings explicitly, so an agent must infer the boundary.

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?

No when-to-use or when-not-to-use guidance. The word 'batch' implies this is for multiple corrections at once versus correct_transcript_phrase_tool or find_replace_transcript_tool, but the agent is left to infer that from the adjective alone, with no stated prerequisites or alternatives.

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