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

The annotations only mark this as non-read-only, so the description carries most of the behavioral burden. It discloses an important side effect: editing TEXT marks the row hand-edited and prevents later replace_transcribed from overwriting it. It does not cover permission needs or time validation rules, which keeps it from a 5.

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 three focused sentences with the core action front-loaded. Every sentence adds useful information, including the time unit and the hand-edit side effect.

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 mutation tool with no output schema and sparse annotations, the description gives enough context to invoke it correctly: row identity is implied, editable fields are listed, and the hand-edit behavior is explained. It could still be strengthened with caption_id semantics and any constraints on start/end values.

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 only 20%, so the description must add meaning, and it does for the editable fields: it clarifies that start_ms and end_ms are timeline milliseconds and that text edits mark the row hand-edited. It does not explicitly explain caption_id or elaborate on project_id beyond the schema, so it stops short of full coverage.

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: edit ONE transcript row, covering text, start, end, or any combination. It also distinguishes this from bulk transcription replacement by naming replace_transcribed and explaining the interaction.

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 makes the primary use case explicit: correcting a single recognizer mistake, and it explains that hand-edited text survives a later replace_transcribed. It does not fully route the agent among other caption-related siblings, but the main alternative is named.

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