memory_get

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

With no annotations, the description anues "verify" against its original sourcefile, a non-obvious behavior that says the tool checks correctness and isn't just a raw accessor. It does not state outverification failures, permissions, or side effects, so the behavior is only partially disclosed.

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 a single sentence with no wasted or repeated information. It fronts the main action and adds only the verification detail in the second clause.

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 tool is simple, but missing include_raw semantics and the format/form of a citation means the agent cannot safely choose correct arguments. The output schema may explain return but no the input field, and no annotation compensates.

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%, and the description only clarifies that the citation targets a Context Lattice item. It does not describe include_raw, its default, or its effect, so an agent is left to guess how to request the raw variant. This is a significant gap for a two-parameter tool.

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 gives a specific action—resolving a single Context Lattice citation—and an additional verification behavior, which separates this from a plain search or sync operation. It does not fully demes multiple beats "Context Lattice" and "original source file" due to jargon, so no full 5.

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 implies it is used when you already have a citation to resolve, rather than when searching or syncing. It never explicitly contrasts with siblings or explains when not to use it; the intended spot in a generate pipeline is inferred.

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