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

Annotations only mark the operation as not read-only, not open-world, and not destructive. The description adds the session-scope ('for the current client thread'), the reserved-selector stripping rule, and the output behavior ('compiled context text only, with no user task attached'), which meaningfully exceeds the annotations.

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?

Three sentences, each earning its place: core action, input caveat, return behavior. No redundancy or 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?

The definition is complete for a single-parameter tool with an output schema. It covers what is loaded, the scope, input formatting, and output type. Minor gaps like session replacement semantics are not needed for correct invocation.

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%, so the baseline is 3. The description adds the practical rule that ctx/context/contexts are reserved type selectors, not IDs, and directs the agent to strip them before passing, which goes beyond the schema's 'Raw Context selector' phrasing.

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 opens with a specific verb and resource: 'Load one or more Oi Contexts as reusable session context for the current client thread.' It also specifies the return shape ('compiled context text only, with no user task attached'), which distinguishes it from other context tools that may attach tasks or fetch raw contexts.

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 provides a clear use case (loading reusable session context) and a caution about reserved selectors, but it never names sibling tools or states when to prefer this over oi.contexts.use, get, or workflows.start-session. Usage context is implied rather than explicit.

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