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

Beyond the readOnly/idempotent annotations, the description discloses the non-obvious behaviors that matter here: the call blocks, returns timedOut: true after timeoutSeconds (default 25, max 30), and orders verification links first in the returned messages. These are exactly the traits an agent needs to plan around a blocking call, and nothing contradicts the 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?

Three tight sentences, front-loaded with the blocking behavior, then the continuation parameter, then the timeout contract. Every clause carries actionable information with no filler.

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 does the necessary work by describing the return shape (messages with extracted codes and links, link ordering, timedOut flag). It stops short of covering failure modes such as invalid tokens or unknown message IDs, which is a minor gap for a four-parameter blocking 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 75%, and the description compensates for the one gap: timeoutSeconds has no schema description, but the description supplies its default (25) and cap (30). It also restates the purpose of 'after' in operational terms (last message ID seen), adding intent beyond the schema's 'only newer messages are returned.'

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 opens with a specific verb and resource: 'Block until the email inbox receives a message, then return new messages with extracted one-time codes and links.' The blocking/waiting semantics plus the OTP-and-link extraction clearly separate it from siblings like list_emails and wait_for_sms.

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?

It tells the agent how to use the tool across calls: pass 'after' with the last seen message ID for newer messages, and call again after a timeout to keep waiting. What's missing is an explicit contrast with list_emails (when to poll the list instead of blocking), so usage context is clear but the alternative isn't named.

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