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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real context beyond that: what the payload contains, that links are signed, and that polling is the intended interaction pattern after start_run. It does not discuss link expiry or how long a run record is retained, which would have pushed it higher.

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 sentences, front-loaded with the resource being read, then a dense value list, then the usage trigger. Every clause carries information; the status enum list is the only verbose part and it earns its place by telling the agent how to interpret results.

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 summarizes the return payload and the status values an agent must branch on, which is the key thing a caller needs. Minor gaps remain around error cases such as an unknown or expired run_id and whether polling is eventually consistent.

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% for the single run_id parameter, so the schema already carries the semantics, and the description adds nothing about the identifier beyond "one run." Baseline 3 is appropriate since the schema does the work here.

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 ("Reads one run") and then enumerates exactly what comes back: status with its full enum, outputs with signed links, QC tool report, credits charged, and error of a failed run. That enumeration makes it unmistakable next to list_runs or start_run without opening either 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?

"Poll it after start_run" gives explicit, actionable guidance and names the sibling that produces the id, which is the dominant usage path. It stops short of saying when not to use it (e.g., to list many runs, use list_runs) and says nothing about polling cadence or terminal-state behavior.

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