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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description reinforces this with 'opens nothing by itself', making clear the tool has no side effects. It adds genuine context beyond annotations by specifying the return content (screens, buttons, fields) and explaining why the official REST API is not an option (Enterprise-only tokens, Threat Intelligence focus). This is solid added value, though it does not say how long or in what format the guide is returned.

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?

Three sentences, roughly 90 words, with the most important fact — that it returns instructions instead of results — buried in the second sentence behind a lead that reads like an actual search. The third sentence about the official API is relevant justification but is long and includes a dated verification stamp that does not help an agent act. Front-loading the 'returns a guide, does not search' point would improve 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, no-output-schema guidance tool, the description covers what is returned, that nothing is opened, and what to do next with the browser tools, plus why the API route is unavailable. What is missing is a pointer to when feedly_list_articles would be the better call and any note on scope (web vs mobile). Overall it is close to complete for the tool's low complexity.

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 and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline for a parameterless tool is 4, and nothing here misrepresents the inputs.

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 verb and resource ('Search articles in the user's own Feedly account') and then clarifies the real behavior: it returns step-by-step instructions rather than performing the search. It separates itself from the cotlet_browser_* siblings by saying those are what actually carry out the action ('opens nothing by itself; then do it with the cotlet_browser_* tools'). It stops short of distinguishing this from feedly_list_articles or cotlet_app_guide, so it is clear but not fully differentiated.

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?

There is an implied two-step workflow: call this to get the Feedly steps, then execute them with cotlet_browser_* in the user's Cloud Browser. That is useful sequencing guidance, but the description never says when this tool should be preferred over feedly_list_articles or cotlet_app_guide, nor when it can be skipped. Usage is inferable rather than explicit.

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