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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: the tool returns procedural guidance (screens, buttons, fields) and performs no action itself, requiring a follow-up cotlet_browser_* call. It doesn't describe the shape of the returned instructions or any auth requirements for the browser session.

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?

The core purpose and the 'returns instructions, opens nothing' behavior are front-loaded well, but the final sentence about Inoreader's REST API/OAuth and lack of an official MCP server is tangential to invoking this tool and reads as research trivia. It's compact overall but that sentence doesn't earn its place for an agent deciding how to call it.

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 zero-parameter, read-only guidance tool with no output schema, the description covers purpose, the instruction-return behavior, and the required follow-up via cotlet_browser_* tools. What's missing is a hint about what the returned steps assume (e.g., that the Inoreader tab must already be open) and which specific browser tool sequence follows.

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?

Zero parameters, so the baseline is 4; there is no parameter meaning to compensate for. The description correctly implies the tool is parameterless and scoped to the user's own account, with no filtering options, which is consistent with the empty schema.

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 gives a specific verb+resource ('Read unread articles in the user's own Inoreader account') and clarifies the account scope. It distinguishes itself from a pure API tool by noting it only returns step-by-step instructions rather than performing the read, though it never names a sibling tool (e.g., inoreader_search_articles or cotlet_browser_read) to contrast with 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?

Clear usage context: call this to get step-by-step Inoreader UI instructions, then execute them with cotlet_browser_* tools in the Cloud Browser. It also states the tool 'opens nothing by itself,' which is a meaningful when/when-not boundary. It stops short of 5 because it doesn't explicitly exclude related siblings like inoreader_search_articles or inoreader_mark_as_read.

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