watch / cursor

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds a genuine behavioral trait beyond that: 'preserving intra-block updates' signals ordering/completeness guarantees for events sharing a block. However, it says nothing about pagination behavior, default limits, or what a caller gets back to advance the cursor.

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 front-loaded sentence with no filler; the cursor constraint and ordering guarantee come in one compact clause. It could still spend one more clause on what is returned to advance the cursor.

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 read-only cursor tool with no output schema, an agent still lacks the return shape (list of events? next cursor?) and the meaning/default of limit. The ordering guarantee is covered, but the pagination contract is not.

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 0%, so the description must compensate. It clarifies the two cursor parameters (since_block, since_log_index) and the ordering semantics between them, but leaves chain_id and limit entirely unexplained 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?

States a specific verb ('Query') and resource ('indexed Vault events') plus the cursor semantics of 'after a specific block and log index'. It implicitly contrasts with watch.poll by describing cursor-based continuation, but never names or explicitly distinguishes itself from that sibling.

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?

'after a specific block and log index' implies incremental pagination use, but there is no explicit when-to-use guidance, no mention of when to prefer watch.poll or history.events, and no prerequisites stated.

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