Get unread counts

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious context beyond that: the counts map to app badges, activity includes likes, replies, new followers and restacks, and 'reading them marks nothing read' clarifies there is no side effect on the unread state.

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, front-loaded with what is counted and followed by the scope of activity types plus the no-mark-as-read note. Minor redundancy between 'badges of the Substack app' and the enumerated categories, but everything earns its place.

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?

There is no output schema, so the return values must be described — and they are: three distinct counts (unread DMs, pending requests, unread activity) plus what counts as activity. That is sufficient for an agent to call it and interpret the result without further detail.

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?

The tool takes zero parameters, which is the baseline-4 case; nothing about arguments needs to be explained and the description wastes no words on them.

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 description states a specific resource and metric: unread direct messages, pending message requests and unread activity counts (badges). It clearly conveys it is a count/summary tool rather than a listing tool, though it never names the nearby siblings (list_conversations, list_activity) that an agent might confuse it with.

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?

Usage is only implied: an agent can infer this is the lightweight way to check whether anything needs attention before calling list_conversations or list_activity. There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named.

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