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

The annotations already declare this as a non-readonly, potentially destructive, idempotent, open-world write operation, so the tool's safety profile is partly clear. The description then adds behavior beyond the annotations: delivery through the brand account, one message per comment, a 7-day limit after the comment, and an optional link button. It still doesn't say what happens when delivery fails or the time limit is exceeded.

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 that lead with the core action, followed by the platform scope and limits, then the optional button and tone rules. There is no filler, but several constraints are compressed into a single run of clauses, which makes the second sentence harder to scan.

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 mutation with no output schema, the definition gives an agent the essentials: what to send, how to obtain the reference, platform scope, the 7-day limit, and tone requirements. The remaining gaps are documentation of button_title and of error and failure behavior, both moderate rather than blocking.

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 25%, and the description compensates for only part of that gap: it ties comment_ref to list_comments, describes button_url as an optional link button, and gives writing guidance for message (short, in the comment's language, no sign-off). Button_title is never mentioned, and the maxLength limits on message and button_title are left to the schema, so the description neither fully explains the parameters nor adds enough detail to close the gap.

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: sending a DM to the author of a comment, using the comment_ref from list_comments. It also scopes the tool precisely (Instagram and Facebook, from the brand account, one message per comment, within 7 days), which is enough to distinguish it from siblings like reply_to_comment or send_message.

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 gives an explicit gating rule: 'Úsala solo cuando el usuario lo pidió', and points to list_comments as the source of comment_ref, which is clear guidance for use. It does not name the closest alternative (reply_to_comment, for a public reply) or state what to do when the 7-day window has expired, so the exclusion is not fully covered.

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