Event journal

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond that: the ring buffer eviction behavior (dropped > 0 means events were evicted), the long-poll timeout semantics, the cursor contract, and the relationship to the push socket. It doesn't describe every edge case, but it discloses the non-obvious behaviors that matter for correct use.

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 well-organized: it front-loads the core backfill behavior and return contract, then filters, then long-polling, then the fallback relationship. Every sentence carries information. It is longer than the typical description, but the complexity of the tool (cursor semantics, ring eviction, long-polling, push fallback) justifies the length. A slight deduction for the dense run-on style in the first sentence.

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, idempotent, non-destructive tool with 100% schema coverage and no output schema, the description is remarkably complete. It explains the return shape, the cursor contract, the eviction failure mode, the long-poll behavior, and the relationship to the push alternative. An agent has everything it needs to call this tool correctly, including how to recover from dropped events.

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 100%, so the schema already documents all six parameters. The description adds meaning for kinds and levels by enumerating the accepted values, and for timeout_ms by explaining the long-poll behavior. However, since the schema already covers the basics, the description's added value is moderate rather than transformative. Baseline 3 is appropriate.

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 a specific verb and resource: 'Backfill from the bridge's event journal', and immediately distinguishes itself from the push alternative. It names the exact return shape and the semantics of each field, so an agent can tell exactly what this tool does and how it differs from siblings like observe or look.

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 explicitly says when to use this tool: as the portable fallback to push, and after any dropped > 0 or seq gap on the socket. It also names the preferred alternative (Monitor on ws://127.0.0.1:<port>/events) and explains the conditions that select between them. This is explicit when/when-not guidance with a named alternative.

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