reply_comment

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

With annotations only declaring readOnly=false/destructive=false, the description carries real behavioral weight: it discloses that resolve=true closes a comment, that a resolved comment in a session requires a lesson, that lesson='new' creates a rule persisting "to the next videos too," and that clicked replies jump to fixed_at. That is substantial state-change disclosure beyond the annotations. It omits permissions, partial-failure behavior, and what a bad lesson/rule id does.

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?

Purpose is front-loaded and almost every clause carries payload, but the body is a single run-on paragraph that crams batch syntax, field semantics, and a lesson decision tree together without line breaks or lists. Dense enough to be hard to parse even though little is redundant.

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 an 11-parameter, nested, batch-style mutation with no output schema, the description covers the workflow, the batch payload shape, the jump target semantics, and the full lesson/rule taxonomy including merge behavior. An agent has enough to construct a correct call without opening anything else.

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 already 100%, so baseline is 3, but the description adds meaning the schema does not: text is "one line ('Caption 20% smaller')", fixed_in is "the new version's file", fixed_at is "the second in it where the fix shows", and it spells out the lesson/missed/'new'/'one-off' decision tree. It also steers toward replies=[...] over the single-id path.

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 opening sentence gives a specific verb and resource ("Reply to review comments and resolve them"), so the agent immediately knows this is the write-side counterpart to get_comments. It is not tautological and is clearly operational. It never names the read sibling (get_comments) explicitly, so it stops short of full sibling differentiation.

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?

Gives concrete when-to-use guidance: "After a round of fixes, send ONE call with replies=[...] for every comment" buckets replies instead of firing one call per comment, and "Unclear comment: ask a question, resolve omitted" covers the edge case. It does not name an alternative tool for reading comments or for re-replying, so alternatives are implied rather than stated.

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