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

Annotations declare readOnlyHint=false with idempotentHint=true, which alone does not tell the agent what actually changes. The description adds a real side effect: 'Shared work for your platform is added to them as you check', disclosing that calling this mutates/expands the queue. It also discloses ordering (most important first). Return format and empty-state behavior remain unstated.

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 short sentences, front-loaded with the primary outcome ('Your unfinished runs, most important first'). The second sentence mixes workflow advice with the tool alternative, which slightly muddies the structure but adds no filler.

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 carries the burden of conveying what comes back. It conveys the queue concept and ordering but not the shape of each item, pagination, or what an empty response looks like given the 'until it is empty' instruction. Adequate but with clear gaps for a tool whose result the agent must act on.

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?

There is a single optional agent_key parameter, and the schema documents it at 100% coverage including the pba_ pattern and the instruction to omit it when the connector URL or Bearer header already carries it. The description adds nothing about this parameter, which is acceptable given the schema is self-sufficient, so the baseline 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?

The description identifies the resource concretely ('your unfinished runs, most important first'), so the agent knows this fetches a prioritized work queue rather than an arbitrary list. It distinguishes itself from next_task by naming it as an alternative. It stops short of an explicit verb like 'returns', but the intent is unambiguous.

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?

It gives a concrete usage loop ('Answer them one after another until it is empty') and names the alternative tool, next_task. However, it never states the condition under which next_task should be preferred over draining the inbox, so the routing decision is left partly to inference.

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