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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered; the description adds the non-obvious fact that the call mutates nothing and only returns textual steps. The trailing note on Feedly's REST API (Enterprise-only tokens, Threat Intelligence focus) explains why the browser route is used, adding useful rationale beyond the annotations.

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?

Purpose and mode of operation are front-loaded in the first sentence, and the browser-handoff instruction follows immediately. The final sentence about Feedly's REST API is somewhat tangential and dense with detail, but it earns partial credit as justification for the guide-then-browser approach.

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 guidance tool with full annotation coverage and no output schema, the description covers what is returned ('screens, buttons, fields') and what happens next. The only material omission is how the agent's target source reaches the tool, which an agent must infer from prior context.

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 normally earns a 4 baseline, but the description never explains how the target source is identified at all (presumably from conversation context or current browser state). For a tool named 'follow source', leaving the source-identification mechanism unstated is a real semantic gap that the empty schema cannot fill.

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 ('Follow source') and, crucially, clarifies the tool's actual nature: it 'Returns how to do it in Feedly step by step' and 'opens nothing by itself'. That distinguishes it cleanly from the sibling feedly_* tools that read or mutate data, and from the cotlet_browser_* tools that perform the action.

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?

Explicitly instructs the agent to pair this with 'the cotlet_browser_* tools in the user's Feedly Cloud Browser' after calling it, which is clear sequencing guidance. It does not name when-not-to-use cases or prerequisites (e.g. that a Feedly session must already be open), so it falls short of full when/when-not coverage.

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