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

Annotations only declare readOnlyHint, but the description adds substantial behavioral context: it explicitly says no message bodies are read and nothing is changed, then defines the semantics of the returned `status` values ('undecided'/'allowed'/'blocked') and of `classification` ('newsletter'/'promotion'), including that classification is only a guess used for sorting and that the owner decides. That is exactly the kind of context annotations cannot carry.

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?

Content is front-loaded: the core action and the read-only guarantee come first, then the output-field semantics, then the presentation instruction. Some sentences are ornate ('this is the question, not the answer'), but each carries real meaning and nothing is 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?

With no output schema, the description does the work of explaining the return shape — sender list, arrival/open counts, `status`, and `classification` — which is more than most tools provide. Minor gaps remain: no mention of the `days` parameter, no pagination or volume/limit behavior, and no explicit pointer to the sibling that reads or records decisions.

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?

There is a single parameter (`days`) with 100% schema description coverage, so the schema already documents the lookback window and its default. The description never mentions the time range, so it adds nothing beyond the structured field; baseline 3 applies when the schema does the heavy lifting.

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: it scans connected mailboxes for newsletters and returns the publications, arrival counts, and open counts. It also implicitly distinguishes itself from the reading/deciding siblings with 'reads no bodies and changes nothing: this is the question, not the answer', though it never names read_my_newsletters or choose_my_newsletters explicitly.

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?

Gives clear usage context — it is the survey/question step, and the closing sentence prescribes exactly what to do with the result (show undecided first, flag promotions, ask which to read). It stops short of naming the sibling that performs the actual reading or the one that records the decision, so the agent must infer the handoff.

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