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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real behavioral value by disclosing that output changes shape over the lifecycle: activity-feed-style progress while running versus a full comparison with recommendation when complete. It stops short of covering rate limits or pagination.

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 tightly written sentences, front-loaded with the core action and then the lifecycle-dependent return shape. No filler or restated name/title content.

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 characterizes both possible return states, which is the key unknown for a polling tool. Annotations cover the safety profile, leaving only minor gaps such as polling cadence and pagination.

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 both parameters (jobId, customerId, including the superadmin-only note) are fully documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline of 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 (poll/get) and resource (benchmark job status and results), which is clearly distinct from the producer sibling benchmark_models and from other status pollers like get_simulation_status. It never names a sibling to disambiguate, so it falls just short of a 5.

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 word 'Poll' implies repeated invocation after benchmark_models, and the jobId schema note ties it back to that tool, so usage is reasonably implied. There is no explicit when/when-not statement or named alternative to route the agent, so it stays at minimum viable.

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