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

The description reveals detailed behavioral traits beyond annotations: resolves ~3s after edit burst settles (debounce rationale), timeout handling, clamping range, default timeout, and exact return shapes for both success and timeout. The annotations (readOnlyHint=true, destructiveHint=false) align with the read-only, non-destructive nature; the description adds actionable timing and return semantics without contradicting 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?

The description is organized with bold section headers ('WHEN TO CALL THIS:', 'BEHAVIOUR:') which front-loads key information. Every sentence is purposeful—no filler. It is longer than average, but the length is justified by the need to convey polling semantics, timeout rules, and the alternative path. Structure and conciseness are excellent.

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?

Despite having no output schema and only 3 params, the description fully covers the tool's role in the board ecosystem: why it exists, when to use it, how the timeout works, and what the return values mean. It also mentions chaining calls on timeout. For a simple long-poll tool, this is a complete and self-contained explanation.

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?

With only 33% schema coverage (only `access_key` has a description), the description compensates by explaining `timeout_ms` clamping and default, and the typical flow implies `board_id` usage. However, `access_key` is not mentioned in the description, leaving its role solely to the schema. Still, the description clarifies the most nuanced parameter (timeout) and the context for board_id, adding value beyond the sparse schema.

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 opens with 'Long-poll: blocks until the next edit lands on this board, then returns,' which clearly identifies the action (wait for update) and the resource (board). It is immediately distinguishable from all sibling tools, which are mutations or reads. The specific verb+resource combination leaves no ambiguity.

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?

Explicit when-to-use guidance is provided: 'if your MCP client does NOT surface notifications/resources/updated events... this tool is how you wait for the human.' It contrasts with the alternative `resources/subscribe` and states a preference: 'If your client DOES deliver resource notifications natively, prefer resources/subscribe'. It also outlines a typical flow and example use cases (turn-based interactions), making usage context unambiguous.

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