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

Annotations only mark it non-read-only and non-destructive; the description carries the real behavioral load: cursor semantics ('only events published AFTER registration are ever delivered'), a 30 registrations/hour rate limit, the ~2,000-entry retention window and what happens to an idle subscription, plus auth via the MCP client's bearer. That is well beyond what the annotations disclose.

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-loads the verb, resource and return value in a single bolded opening sentence, then layers usage, return shape, vocabulary and limits. It is long and slightly repetitive — it restates list_options("event_types") guidance already present in the schema — but nearly every sentence adds operational value rather than padding.

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?

Although an output schema exists, the description still supplies what matters for correct invocation: the return shape, the persistence of subscription_id (no list endpoint), which tools consume it, auth, rate limit, and the resumption/retention caveat. Nothing needed to call it correctly is missing.

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 baseline is 3, but the description adds usable semantics: empty body listens to everything, the vocabulary rules (report_plan as 'stream full research as it is minted', a family for 'everything earnings-related', symbols for a watchlist), and the filter-normalisation behaviour (topics lower-cased, symbols upper-cased, duplicates dropped).

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 ('Save a realtime-event filter server-side') and the artifact produced (`subscription_id`), plus the underlying endpoint. It explicitly differentiates itself from the siblings stream_events, stream_event_subscription and delete_event_subscription, so an agent can pick it without opening another 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?

Gives an explicit alternative and the condition that selects it: 'For a live-streaming ask, the default is a dashboard... that loops stream_events itself — see stream_events. Register a subscription when the user wants a saved filter that resumes across sessions.' When-to-use and when-not-to-use are both stated.

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