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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavioral value beyond that: it discloses that a pending job yields ready=false with partial evidence and search outcomes and that the read does not fail. That is exactly the kind of non-obvious behavior an agent needs.

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 action front-loaded and the pending-state caveat following. No filler, though it could be marginally sharper by naming the sibling it differs from.

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?

Since an output schema exists, the description is not obligated to explain the return shape, yet it usefully flags the ready flag and partial results for the pending case. It is complete enough to call correctly, with only the relationship to research_status left unstated.

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?

With a single parameter at 100% schema description coverage ('Owner-scoped research job ID'), the schema already carries the meaning. The description references 'one of your research jobs' but adds no format or syntax detail beyond the schema, so 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?

States a specific verb ('Read') and resource ('all retained results for one of your research jobs'), clearly conveying what it returns. It does not, however, differentiate itself from the close sibling research_status, so the agent must infer the split between reading results and checking job state.

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 phrase 'for one of your research jobs' implies the calling context (after research_start), and the pending-work note implies it can be polled. But no explicit when-to-use/when-not guidance or alternative (research_status) is named, leaving usage to inference.

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