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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one useful trait — that the queue position is a point-in-time snapshot, i.e. non-blocking — but omits what happens for unknown/completed tasks and any polling or rate-limit behavior.

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 with the core capability front-loaded and no filler. The second sentence is short but circular, so it spends words without earning them.

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?

An output schema exists, so return values need not be explained. However, for a status-polling tool the description should still cover task_id provenance and whether repeated calls are expected; those gaps leave it only minimally adequate.

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 0%, so the description must compensate for the single required task_id and does not — it never mentions the parameter or where to obtain it. The schema's uuid format and pattern carry the only meaning available.

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: return queue and execution status, plus the current snapshot queue position. This implicitly separates it from agent_task_result and agent_task_events, though no sibling is named explicitly.

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?

"Use this only when status is useful to the user or downstream AI" is circular — status is useful when status is useful. There is no guidance on polling cadence, on when to prefer agent_task_events or agent_task_result, or on terminal-state handling, even though those siblings exist.

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