suggest_rules

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

With no annotations present, the description carries the full burden and does address the highest-risk question: it never mutates ("Nothing is created until create_rule is called") and it de-duplicates against existing rules. It does not disclose result volume, cost of scanning, or what the proposal looks like, so a little behavioral ground is left uncovered.

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?

Two short sentences with no filler; the core behavior leads and the routing caveat follows. The second sentence depends on a parameter name an agent cannot resolve from the schema, which slightly muddies otherwise tight structure.

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?

The tool is a read-only suggestion generator with three undocumented, optional parameters and no output schema, and the description never says what a proposal contains or how many come back. It covers purpose, non-destructiveness, and one alternative path well, but leaves parameter interpretation and return shape to inference.

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 0% across three parameters (scan, folder, min_count), so the description must compensate and largely does not. "Senders that flood a folder" hints at folder and min_count semantics, but scan is never mentioned and no units, defaults, or thresholds are explained. It also references an undefined `unsubscribe_first` field that does not appear in the input schema, adding confusion.

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 ("Propose") and a specific output ("create_rule arguments") scoped to "senders that flood a folder," and adds the exclusion "skipping senders already covered by a rule." This clearly separates it from create_rule (which actually writes) and from sender_stats/find_bulk_mail siblings that only report counts.

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?

Explicitly routes the agent: when unsubscribe_first is true, use find_unsubscribable then unsubscribe instead, with the reason given ("a rule only hides the mail"). It also clarifies the read-only preview role via "Nothing is created until create_rule is called." It offers no guidance on choosing between this and sibling analyzers like sender_stats or find_bulk_mail.

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