Poll inbox until a matching email arrives. Ideal for OTP and verification codes.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Keyword to match in subject or body (e.g. 'verify', 'code') | |
| from | No | Expected sender address | |
| timeout_seconds | No | Max seconds to wait (default 60) |
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 provided, the description carries the full burden of behavioral disclosure. It only states the basic polling behavior but does not disclose the timeout behavior, what happens on no match, whether it is non-destructive, or whether it blocks. This is a significant gap for a polling operation with a timeout_seconds parameter.
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 only two sentences and immediately states the core action and common use case. Every word adds value, with no filler or redundant restatement of the tool name.
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 tool has no output schema and no annotations, the description must explain what the tool returns upon success or timeout, plus any side effects. It only covers the purpose and typical use case, leaving out critical operational details like what happens when timeout_seconds elapses or how strict the matching is. This makes it incomplete for an agent to confidently invoke the 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?
The schema has 100% description coverage for its 3 parameters, so the baseline is 3. The description does not add additional meaning beyond the schema; it just says 'matching email' without detailing how q and from are used. It neither enhances nor contradicts the schema, so a neutral 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 begins with a specific verb and resource: 'Poll inbox until a matching email arrives.' It clearly distinguishes this from sibling tools like read_inbox or get_email, which are likely non-blocking retrieval operations, while this tool is explicitly a wait-for-condition operation.
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 phrase 'Ideal for OTP and verification codes' provides clear context for when to use this tool, which helps the agent choose it over reading an inbox directly. However, it doesn't explicitly state when NOT to use it or name alternative tools, so it lacks the exclusionary guidance needed for a 5.
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 targets a distinct action on emails or account management. read_inbox and read_sent clearly separate incoming from outgoing, while get_email and delete_email operate on specific email IDs. wait_for_email serves a unique polling purpose, and register_email is distinctly for account creation.
All tool names follow a consistent verb_noun pattern using lowercase snake_case. Examples include delete_email, send_email, and wait_for_email. The use of read_ for list operations and get_ for retrieval is semantically appropriate and maintains a uniform style.
The set of 7 tools is well-scoped for an email management server. It covers the essential actions (register, send, read, retrieve, delete, poll) without unnecessary redundancy or bloat. The count is within the ideal range for a focused MCP server.
The tool surface covers the core email lifecycle: account creation, sending, listing (inbox/sent), fetching full content, deleting, and waiting for incoming messages. Minor gaps like attachment handling or account info retrieval are not critical for typical email workflows, so they are acceptable.