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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so the safety profile is covered. The description adds two genuinely useful facts beyond that: it is 'Free' and it consumes 'no browser session', which matters for cost/rate budgeting. It does not say whether the returned guidance is cached per session or whether repeat calls return updated content.

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 intent sentence is front-loaded and the call trigger appears early, but the opening sentence is an overstuffed clause chain of six comma-separated items and the trailing Feedly action enumeration is long and app-specific, reading more like catalog content than selection guidance. It is not padded with fluff, yet it could lose the item list without losing decision-relevant information.

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 carries the return-value burden and does so by enumerating the guide's contents (browser choice, sign-in link, method, screens/menus/actions, notes, dedicated tools). For a zero-required-parameter, read-only guidance tool, an agent has everything needed to decide to call it and to interpret the response.

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 coverage is 100% and both parameters are already documented (app with maxLength 120 and a stated Feedly default, task with maxLength 500). The description only indirectly adds meaning, hinting that an app outside the catalog falls back to the general method and enumerating the Feedly action set, but it never explains what 'task' changes in the output or that app accepts a slug. Baseline 3 applies when the schema does the explanatory work.

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 uses a concrete framing ('how to work in an app') and enumerates what the guide returns: which browser per workspace, the sign-in link, the step-by-step method, the app's screens/menus/actions, notes, and the app's dedicated tools. That distinguishes it from the action-executing siblings like cotlet_browser_click or feedly_save_article_to_board, though the phrasing is a dense run-on rather than a crisp verb+resource statement.

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 gives an explicit trigger — 'Call it before the first browser step in an app' — and states coverage breadth ('Works for any web app; one outside Cotlet's catalog gets the general method'), which tells the agent it is safe to use even on unfamiliar apps. It does not name when to skip it (e.g., already called in this session, or when a dedicated feedly_* tool directly answers the request), which keeps it short of a 5.

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