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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the result is only available 'once done' (i.e., non-blocking polling semantics) and that it returns progress, but says nothing about auth requirements beyond the schema, whether polling is rate-limited, or how it differs behaviorally from host.runs.wait.

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?

A single sentence with the core action and resource front-loaded; the em-dash aside about run origin earns its place as disambiguation. Slightly dense but no filler sentences.

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?

There is no output schema and no annotations, so the description must cover return semantics; it names status, progress, and result but gives no shape for the status values or progress representation. For a simple two-parameter read tool this is adequate but leaves the agent guessing at the payload structure.

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 both parameters (run_id, tenant_key) are documented there, so the schema does the heavy lifting. The description only adds the phrase 'by id', which does not extend meaning beyond the schema; 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?

States a specific verb (Read) and resource (one run) and enumerates what is retrieved: status, progress, and result once done. It also ties the resource to its origin (host.tool_call async, scheduled/triggered execution), which cleanly separates it from host.runs.list, host.runs.cancel, and host.runs.purge.

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 implies usage by explaining where a run id comes from (an async host.tool_call or a scheduled/triggered execution), which tells the agent when it will have an id to query. However, it never names alternatives such as host.runs.wait (blocking) or host.runs.list (enumerate runs), leaving the choice between polling and waiting to inference.

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