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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that — the polling pattern and the terminal-state vocabulary — but says nothing about failure modes (unknown run_id), polling cadence, or whether intermediate states are enumerable.

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?

Two tight sentences: the return content is front-loaded and the polling instruction follows as actionable guidance. No filler or restatement of the title.

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 usefully enumerates the returned fields and terminal states, which is what an agent needs to decide when to stop polling. It stops short of covering non-terminal state names or error behavior for invalid/expired runs.

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 100% and the single run_id parameter is documented in the schema as coming from alterlab_run_create, so the description carries no extra parameter burden. Baseline 3 applies since it adds no syntax or format detail beyond the schema.

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?

Specific verb and resource ('Get the current state of a run') plus an explicit enumeration of what is returned (status, estimate, credits spent, per-step summary), which separates it from mutation siblings like alterlab_run_create or alterlab_run_cancel.

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?

Explicitly instructs 'Poll until the state is terminal' and names the five terminal states, giving a clear operating loop. It does not, however, say when to prefer this over siblings such as alterlab_run_stream or alterlab_job.

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