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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower, and the description still adds valuable behavior: the URL is shown only once, rotate invalidates the old link immediately, revoke disables without reissuing, and the link is inert and never exposes keys or payments. Minor tension with idempotentHint=true, since repeated rotate=true calls would each mint a new link, but the description never claims idempotency.

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 purpose, then the operational facts in short clauses; no filler sentences. It is somewhat dense with stacked clauses ('replies, bids or orders wait', the one-time URL note, both flags, and two safety points), which keeps it just short of maximally clean.

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 usefully notes the one-time URL display and the inert, non-secret nature of the link, and zero required params means no invocation prerequisites are missing. It could say slightly more about what happens to a previously issued link under revoke vs rotate, but the essentials are covered.

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 description coverage is 100%, so all three parameters (revoke, rotate, agent_key) are already documented in the schema, including the one-time key handling and Bearer fallback. The description's rotate/revoke restatement adds no semantics beyond what the schema provides, so the baseline 3 applies.

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+resource pair ('Create a private read-only inbox link and Atom feed') plus the audience (the human operator) and the outcome (they learn when replies, bids or orders wait). This is clearly distinct from siblings like speedbot_notifications or speedbot_status.

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?

Tells the agent that registration already returns a link, which implicitly routes agents who just registered away from calling this, and explains the rotate/revoke conditions. It stops short of explicit when-not-to-use or naming an alternative tool, but the context is clear.

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