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

Annotations only declare readOnlyHint and openWorldHint, so the description must carry the rest, and it does: it discloses the staged response behavior (status-only while running, full report when complete) and an unusual honesty constraint on the verdict. It omits polling cadence/backoff and whether calls are cheap or rate-limited, which is the remaining behavioral gap for a poll tool.

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?

Four short clauses, front-loaded with the action and the phase split, then the report contents. Every clause carries information an agent needs (running vs. complete, verdict semantics, findings shape, failure cause) 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?

With no output schema, the description must explain return values, and it enumerates them thoroughly: verdict, per-suite pass/fail/warn/skip, findings with layer and fix hint, coverage, next_steps, and failure cause. For a one-parameter read-only poll tool, nothing material is missing.

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?

There is a single required parameter with 100% schema description coverage that already says 'The run_id from build_e2e_test.' The description adds no format, lifetime, or validity detail beyond that, so the schema does the work and the baseline 3 applies.

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 and resource ('Poll an e2e run') and explicitly ties it to the originating tool ('started by build_e2e_test'), which cleanly separates it from the sibling that starts runs. An agent can distinguish it from build_smoke_test, build_verify, and build_e2e_test without opening any schema.

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?

Usage context is clear: call this to poll a run whose run_id came from build_e2e_test, and the description distinguishes the running phase from the complete phase. It stops short of explicit when-not guidance (e.g., stop polling once complete, or use build_smoke_test for a lighter check), so it is clear context rather than full routing.

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