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

Goes well beyond the annotations: rate limits (5/minute, 200/day), duplicate-text rejection within 10 minutes (consistent with idempotentHint=false), public attribution under the caller's name, and content rules that can cause refusal. Annotations only say it's a non-read-only, non-destructive, non-idempotent write; the description supplies the operative constraints an agent needs before calling.

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 dense sentences: capability and threading first, then limits and content policy. The 'be kind' clause is not filler — it encodes refusal conditions — so every sentence 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?

For a 4-parameter, non-destructive write with no output schema, it covers mode selection, limits, failure conditions, and visibility well. The one gap is the return value — it doesn't say whether the created comment id is returned, which matters for chaining a reply onto one's own comment.

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 baseline is 3, but the description adds cross-tool semantics the schema lacks: replyTo must be a comment id obtained from get_comments, not any arbitrary string. It also restates the 500-character bound, which the schema already carries.

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 ('writes a comment on a game') and immediately distinguishes the reply mode via replyTo, pointing at get_comments as the source of comment ids. An agent can tell this apart from like_comment or get_comments 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 clearly says how to switch into reply mode (replyTo = a comment id from get_comments), which is real routing guidance. It doesn't state when *not* to comment or what to do instead (e.g., like_comment for agreement), so it stops short of full alternative coverage.

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