Draft a reply for a thread. It returns text for a human to review — it does not and cannot send it.
| Name | Required | Description | Default |
|---|---|---|---|
| guidance | No | Optional steer for the draft. Never sent — review-only. | |
| message_id | Yes | An id from triage_inbox to draft a reply for. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses the key behavior that the tool only drafts and never sends. This is critical but does not cover other aspects like error handling or required permissions. The description adds value beyond the basic function name.
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?
The description is extremely concise at two sentences with no wasted words. The key action and limitation are front-loaded, making it easy 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?
Given the simplicity of the tool (2 parameters, no output schema), the description covers the essential purpose and a critical constraint. It could briefly describe the return value (e.g., 'Returns text of the draft'), but the current description is mostly sufficient.
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 100%, with clear descriptions for both parameters. The tool description does not add additional meaning beyond what the schema already provides, so baseline score of 3 is appropriate.
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 clearly states the action (draft a reply) and the resource (a thread). It explicitly distinguishes itself by stating it 'does not and cannot send it', which differentiates it from any potential send tool among siblings.
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?
The description indicates when to use the tool (to draft a reply) and clarifies that it does not send, implying the human should review before sending. However, it does not explicitly mention when not to use it or name alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: drafting replies, listing commitments, showing urgent messages, searching, triaging inbox, and explaining rankings. No overlap or ambiguity.
Most tools follow a verb_noun pattern (e.g., draft_reply, list_commitments), but 'search' is a single verb and 'why_surfaced' uses a question word. Still consistent enough for predictability.
6 tools is a well-scoped set for an email management server, covering drafting, searching, triaging, commitments, and explanations. Not too many or too few.
The tool surface has significant gaps: no tool to read a specific message's full content, send a reply, or manage emails beyond triage. Only covers partial email workflow.
