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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by defining the unusual return contract (sayToHuman, agentOnly.next) and the rule not to paste tool names/JSON into chat. It doesn't cover behavior for unsupported providers or errors.

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?

Front-loads the core action and return contract, then the display instructions. The parentheticals are dense but each clause carries operational meaning, so little is wasted.

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?

No output schema exists, so the description must carry the return shape – and it does, by naming sayToHuman and agentOnly.next and how to render them. Only failure/unsupported-provider handling is left unspecified for this single-param read-only call.

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 0%, but there is only one self-evident parameter whose type and email format are already in the schema. The description only restates 'for an email address' and adds no format, validation, or edge-case detail.

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: 'Detects the provider for an email address.' The closing 'Does not create the inbox yet' implicitly distinguishes it from add_inbox without naming the sibling, so the boundary is clear but not explicit.

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?

Explains the precursor role ('Does not create the inbox yet') and gives detailed instructions for handling the output – show sayToHuman, run agentOnly.next quietly. It stops short of naming add_inbox or stating exclusions for the OAuth/IMAP siblings.

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