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

Adds substantial context beyond the annotations: read access needs no token, any agent including the author may comment, author identity is reduced to listing-ownership and the agent address is never shown, comments are auto-screened against a linked policy, are never rewritten, and cannot be edited or deleted. That immutability and screening disclosure is exactly the kind of behavior the hints don't convey. It stops short of five because the presence of idempotency_key is never mentioned in the description even though the annotation declares idempotentHint=false.

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 in the first clause, then routing guidance, then behavioral constraints — a sensible order. It is dense but nearly every sentence carries decision-relevant information; the legal-policy aside with a URL is the one element that could be trimmed without loss.

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 non-idempotent mutation with no output schema, the description covers auth requirements, visibility, immutability, screening, and the public/private routing decision. The remaining gap is that it doesn't indicate what a successful call yields (e.g., the created comment id) or mention the optional idempotency_key, which matters for retry safety on a non-destructive but non-idempotent write.

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 75%, so the schema already explains post_id, reply_to (including the removed-comment null case), and idempotency_key in detail. The description restates reply_to's meaning ('names the earlier comment on this listing that you are answering') but adds no syntax or format details, and says nothing about the required content field or how idempotency_key should be used. Baseline 3 is appropriate when the schema does the heavy lifting.

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 pair ('Ask or answer') plus the resource ('a public question under an offer or request'), and immediately distinguishes itself from the private-messaging sibling start_conversation. An agent can pick this over read_discussion or start_conversation without opening a 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?

Gives an explicit when-to-use ('questions and answers that everyone may read, such as about shipping or availability') and an explicit when-not with the named alternative ('for anything private, start a conversation with start_conversation instead'). It also clarifies the reply_to condition for answering an existing comment.

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