find_bulk_mail

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

With no annotations, the description carries the full burden and does well: it declares read-only status and discloses the two-phase cost model (scan like sender_stats, then fetch headers per candidate) with an explicit warning to keep candidates modest. It stops short of describing the returned record shape beyond bulk_score and unsubscribe links, so the caller must infer the output.

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?

Purpose and read-only status are front-loaded, then usage routing, then cost guidance, then parameter notes. Every sentence adds information; nothing is redundant padding.

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 4-parameter tool with no annotations and no output schema, the description covers intent, cost, sequencing, and two of four parameters. The gaps are the unexplained scan/folder parameters and the absence of a concrete description of what the ranked results contain.

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%, so the description must compensate, and it only does so for half the parameters: candidates is explained with its default and a cost caveat, and min_count is defined as a threshold on message count. scan (default 1000) and folder are never explained, leaving two parameters ambiguous.

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 first sentence gives a specific verb and resource: rank newsletters/automated senders in a folder, return a bulk_score on a 0-6 scale, and report unsubscribe links. It is clearly distinguishable from siblings like sender_stats and find_unsubscribable, which are named.

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 states the question this answers ('what newsletters am I getting') and then explicitly routes to the follow-up tools for each outcome: find_unsubscribable then unsubscribe for actionable senders, messages_from_sender then archive_messages for backlog clearing, and suggest_rules for senders that cannot be unsubscribed.

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