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

With no annotations, the description carries the full burden. It does disclose useful behavior beyond the schema — that regexes are JavaScript-flavored, that they are ad-hoc/not persisted, and that only the first capture/match per field is returned — but says nothing about permission requirements, behavior when a field's regex does not match, or how errors are surfaced.

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?

A single front-loaded sentence with no filler; the mechanism and return behavior both land before the sentence ends.

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 tool with a nested-object parameter, no output schema, and no annotations, the description should be more complete. It omits the no-match outcome, whether the whole match or capture group 1 is returned ("first capture/match" is ambiguous), and the result shape, which the absent output schema leaves unexplained.

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 only 33%: inboxId and messageId have no descriptions in either place. The description and schema both explain the fields map (name -> regex source, first capture returned), which is meaningful, but the description adds little for the two undocumented identifier parameters beyond implying they address the target message.

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: apply named regexes to a message body and return the first capture/match per field. The word "ad-hoc" implicitly separates it from the persistent-rule sibling manage_extract_rules, but that sibling is never named, so the differentiation is left to inference.

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?

"Ad-hoc" hints that this is for one-off extraction rather than saved rules, which points away from manage_extract_rules, but there is no explicit when-to-use or when-not guidance. An agent must guess whether to persist a rule first or use wait_for_code instead for verification codes.

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