report_generate

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

Goes well beyond the supplied readOnlyHint/openWorldHint annotations: link expiry (~1 hour), typical 5-30 s runtime, the zabbix://reports/<id> resource and download_url/download_url_unavailable response fields, receipts for file/email delivery, and refusal behavior when those are unconfigured. There is a mild tension worth noting - save_to_file writes to the server filesystem and email_to sends mail, which is not purely read-only - but the description discloses both side effects explicitly, so the agent is not misled.

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?

Front-loaded with purpose and report types, then organized by delivery mode, then runtime/task behavior - a logical reading order with no filler sentences. It is on the long side for a tool description and could compress the delivery-mode paragraph, but each sentence carries operational information.

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 carries the return-value burden and does so thoroughly: resource link, optional download_url, the download_url_unavailable explanation field, and short receipts for file/email modes. Combined with runtime expectations, expiry, and the task-handle alternative, an agent has everything needed to invoke and interpret this tool.

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 the baseline is 3; the description still adds real meaning by explaining the tradeoff behind as_link (context bloat vs. practicality), that email_to requires [reporting.email] plus allowed_recipients, and that save_to_file requires [reporting].output_dir and returns a path. It does not add anything for period, server, company, or hostgroupid beyond the schema, which is fine.

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 artifact ('Generate a PDF report from Zabbix monitoring data') and enumerates the four concrete report types (availability, capacity_host, capacity_network, backup), so an agent knows exactly what will be produced. It also distinguishes itself implicitly from the sibling report_get, which retrieves an existing report rather than creating one.

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 clear conditional guidance for each delivery mode: use the default link path, switch to inline base64 only for small reports, enable save_to_file or email_to only when the operator configured them, and use the tasks extension when behind a proxy with short timeouts. It does not explicitly state when to prefer report_generate over report_get or other dashboard/render siblings, which is the only missing routing cue.

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