watch / poll

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds two genuinely new facts: the data comes from a local index (not live RPC), and polling cadence is external to the tool. It says nothing about result shape, ordering, or truncation behavior when limit is reached.

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?

A single compact sentence with the core scope front-loaded and no filler. It is efficient, though the terseness is partly the cause of the uncovered parameters.

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?

No output schema exists, so the description should sketch the return shape and whether results are ordered or capped, which it does not. It does correctly convey the incremental-poll contract, leaving it adequate but incomplete for a 3-parameter event tool.

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 0%, so the description carries the full burden, yet it only explains since_block ('newer than a given block'). chain_id and especially limit (units? default? truncation?) are left entirely undocumented in both schema and description.

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 verb (check) and resource (locally indexed events newer than a given block), which is far more informative than the title 'watch / poll'. It implicitly distinguishes the pull-based polling model from the sibling watch.cursor, though it never names that sibling or history.events.

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?

'caller schedules repeated polls' gives useful usage context: this tool does one incremental read, and the loop is the caller's responsibility. However, there is no explicit guidance on when to prefer watch.poll over watch.cursor or history.events, and no stated prerequisites.

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