session_wait

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

With no annotations, the description carries the full burden and does so well: mesh wake-on-write is ON by default, the opt-out env var is named, the degraded behavior is described, and the crucial side effect that the cursor advances (events consumed) is disclosed. It also flags the untrusted-payload safety requirement, which is unusual and valuable context beyond the schema.

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 front-loaded: core long-poll behavior comes first, followed by configuration/fallback details, then the security caveat. Every sentence conveys distinct operational information with no filler.

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 blocking-read tool with no annotations and no output schema, the description supplies what an agent needs: when it returns, what it returns (events addressed to the session), that consumption advances the cursor, and how behavior changes when push is disabled. The security warning about untrusted payloads closes an important gap.

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 session_id, timeout_ms, and project_path are already fully documented in the schema. The description reinforces timeout behavior ('or timeout_ms elapses') but adds no new syntax, format, or constraint information beyond what the schema provides, making the baseline 3 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 states a specific verb ('Long-poll') and resource ('the session bus') and precisely defines the return semantics: immediate when events are pending, otherwise blocking until an event or timeout. It distinguishes itself from session_events by noting consumption is identical but the wait behavior differs.

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 conditions are given for selecting this tool: use it to wait for addressed events, with immediate return when pending. It also names a concrete alternative path ('degrades to a single session_events read') and the exact condition that triggers it (EGC_MESH_PUSH=0), leaving little to inference.

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