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

Annotations provide readOnlyHint=true and openWorldHint=false, but the description goes far beyond that. It discloses that signals may have expired (status), that nothing is skipped even on the free tier, that there is a standard delay, that the cursor is a compound of timestamp and id, and that server_timestamp is unsafe as a cursor. This is rich behavioral context not captured by 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?

The description is dense but every sentence adds value: it opens with the purpose, then details cursor usage, pagination, delay, and a warning. It is front-loaded with the 'Polling alternative' tag and the core function. While it is longer than average, the technical complexity justifies the length; it is not padded.

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 tool with cursor-based pagination, ordering, expiry, delay, and safe-cursor semantics, the description covers all critical aspects. It explains the ordering (oldest first), the has_more flag, the limit range, the delay behavior, and the unsafe cursor warning. It even notes that expired signals are included and references the status field. With an output schema present, the description is effectively complete for correct invocation.

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 input schema has 0% description coverage, so the description must carry the burden. It explains since_timestamp (unix epoch seconds), since_id (from previous call's cursor_id), limit (1-100, default 100), and the next_cursor format. It does not explain asset or signal_type, which are optional filters, but the core cursor mechanics are well-covered. This is a strong compensation for the schema gap.

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 purpose: it is a polling alternative to the /stream WebSocket that walks the signal stream in emission order from a cursor. It clearly differentiates itself from the many sibling get_* tools by focusing on cursor-based retrieval of signals since a timestamp, and even notes it returns expired signals. This is a precise verb+resource definition.

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?

The description gives explicit usage instructions: how to set the cursor (since_timestamp and since_id), how to paginate (keep calling while has_more), and warns against using server_timestamp as a cursor. It implies it is for polling scenarios versus streaming, but does not explicitly name alternatives like list_signals or get_signal. Still, the usage context is clear and actionable.

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