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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds what is actually destroyed (existing content is overwritten), that nothing is dispatched, and that the response contains a validation report. It does not cover authorization requirements or whether a failed import_url fetch leaves the campaign untouched.

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 sentences, front-loaded with a 'WRITE:' marker, with no redundant restatement of the title or schema fields. Each clause carries distinct information: mode selection, side-effect boundary, and response contents.

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?

With no output schema, the description usefully summarizes what the reply's report contains (javascript, missing unsubscribe link, missing images). It could say more about failure behavior for a bad import_url or whether content is left intact on validation errors.

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 the baseline is 3, but the description adds genuinely new meaning the schema lacks: the precedence rule that html overrides import_url when both are provided. It adds nothing about inline_css beyond the schema text.

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 ('replace a campaign's content') and gives the two input modes with a precedence rule. 'Does not send anything' distinguishes it from laposta_send_test_email, and the word 'replace' distinguishes it from the read-only sibling laposta_get_campaign_content.

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 a concrete selection rule between the two content sources ('html wins if both are given') and a clear negative boundary ('Does not send anything'). It does not explicitly name sibling tools to use instead for reading or sending, so it stops short of a full when/when-not map.

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