Reply as a draft

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

Annotations are all false, so the description carries the behavioral disclosure burden. It does this well: it reveals this is a draft-creating operation that never sends ('Nothing is sent'), states that In-Reply-To/References, 'Re:' subject, recipients, and quoted original are set by the server (versus by the caller), and implies the quote is automatic. These are genuinely useful behavioral disclosures beyond what annotations provide. No contradiction with annotations.

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 with no filler. The first sentence front-loads the core action, destination, and server-set fields; the second adds concrete trigger phrases and a safety note ('Nothing is sent'). While dense, every clause earns its place. Slightly packed — a reader must parse several comma-separated facts — but not verbose.

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 9-parameter tool with no output schema, the description covers the essential behavioral context: where the draft is saved, that nothing is sent, that headers/quote are auto-set, and when to trigger it. The remaining parameters (folder defaults, attachments, html, lang) are adequately documented by the 89% schema coverage. The lack of an output schema is partially offset because the description clarifies the 'no send' guarantee, so an agent understands the expected effect.

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 high at 89%, so the schema documents most parameters thoroughly, making the baseline 3 appropriate. The description adds modest semantic value by telling the agent that recipients are 'sender, or everyone with reply_all' — mapping to the reply_all parameter — and that the quoted original is auto-set, relating to the quote parameter. But it doesn't cover the remaining parameter nuances in depth, which the schema handles.

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: 'Saves a reply to a specific message into Drafts, in the same thread.' It enumerates what the server sets (In-Reply-To/References, 'Re:' subject, recipients, quoted original), which clearly distinguishes it from siblings like reply_send (which would send) and create_draft (which creates a blank draft rather than a threaded reply). The closing 'Nothing is sent' removes any ambiguity about side effects.

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?

Provides explicit trigger phrases for when to use: "Use this whenever the owner says 'reply / answer / write a draft' ('odpověz', 'napiš koncept')." This gives clear activation context. However, it does not name alternatives or state when NOT to use it — notably, it doesn't distinguish itself from reply_send (when the user wants to send rather than draft) or from create_draft. Clear context but no explicit exclusions.

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