File email to property

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

Annotations already declare this is a non-destructive write (readOnlyHint=false, destructiveHint=false), and the description adds real behavioral value beyond them: attachments are materialized as separate documents with a specific naming pattern '<date> - <subject> - <file>'. That side-effect disclosure is exactly the kind of thing annotations cannot convey. It stops short of stating permission/approval requirements or failure behavior.

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?

Three tight sentences: action and target first, then the input-mode alternative, then the attachment side effect. No filler and nothing buried.

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 mutation tool with 11 parameters and no output schema, the description covers the essential call-shape decisions (entity target, input mode, attachment handling), while the schema covers confirm and entityType. Missing context on required approval/session state and what happens on partial failure keeps it below full marks.

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 27% across 11 parameters, so the description has to carry weight — and it does: it establishes the mutually exclusive input modes (raw emlBase64 vs. discrete subject/from/to/date/text/html fields), which the schema does not express, plus the attachment naming rule. It leaves entityType, entityId, confirm, and the attachment object shape unaddressed, keeping it short of a 5.

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?

The description gives a specific verb and resource ('Store an email (and its attachments) as documents on a property or tenant'), which is clearly distinguishable from generic siblings like upload_document. However, it never differentiates itself from the close siblings add_communication_message, update_communication, or upload_document, which an agent will likely weigh against it.

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?

There is no when-to-use/when-not-to-use guidance and no mention of alternatives, even though the sibling list contains several plausible substitutes (upload_document, add_communication_message). The only conditional guidance given ('Pass either emlBase64 ... or subject/from/to...') is about parameter form, not tool selection.

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