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

Annotations already cover readOnly/destructive/idempotent, but the description adds business-critical context beyond them: nothing is saved, no credits are spent, and it is org-scoped so no accountId is needed. It also explains the two possible response shapes and what the agent should do with each.

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?

Front-loaded with the when-to-use condition, followed by behavior and the branch handling for 'candidates'. Multi-sentence but every sentence earns its place—no filler or redundancy.

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?

Given the rich annotations and an output schema, the description is complete for a one-parameter read-only discovery tool. It covers preconditions, both response branches, next steps, and safety/cost implications.

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%, so the schema documents the single url parameter. The description adds useful semantics beyond that—explaining that a plain page URL triggers feed discovery, which clarifies why either URL type is accepted and what happens with each.

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 (preview) and resource (feed), and immediately distinguishes itself from connect_feed as the non-committal inspection step. An agent can tell exactly what it does without opening either schema.

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 names the trigger conditions (user gave a website/blog URL instead of a feed URL, or wants to confirm feed contents before subscribing) and the alternative (connect_feed). It also prescribes the follow-up action for the 'candidates' case, leaving nothing to inference.

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