context_pack

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

With no annotations, the description carries the full burden, and it adds meaningful behavioral context: returned history should be treated as cited evidence rather than instructions, and user request/policies take precedence. It also signals that results are ranked. It does not mention side effects, but 'load' implies a read-like operation and the trust semantics are more valuable than a generic read-only hint.

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?

The description is compact and well-structured: it front-loads the primary action, then gives a precise usage trigger, then adds an important trust/precedence caveat. Every sentence contributes value and there is no redundancy.

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 value details are covered elsewhere. However, with seven parameters and zero schema descriptions, the description alone is not sufficient for an agent to correctly construct a call; it lacks guidance on which refs are relevant, what 'ranked' means concretely, and how this differs from context_read/context_search. The usage and trust guidance helps but leaves notable gaps.

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 seven undocumented parameters. It does not explain space_ref, query, max_items, token_budget, or the optional ref scoping fields. Parameter names are somewhat self-explanatory, but no actual semantic guidance is provided.

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 uses a specific verb ('Load') and identifies a clear resource ('a ranked working pack from a Lightbulb Context Space'). It states what the tool does without being a tautology, though it does not explicitly differentiate itself from related siblings like context_read or context_search.

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 explicit guidance on when to use the tool: 'Use before a substantial reasoning step or when the prompt changes.' It does not name alternative tools or exclusions, but the timing guidance is concrete and actionable.

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