memory_eval_long_context

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

The description states that the tool 'Saves N records', which implies write/create behavior, but the annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. This is a direct contradiction and could mislead an agent about side effects.

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 brief and mostly to the point, but the opening 'v11.0 Phase 8' is version/phase noise that does not help an agent. The remaining sentences are functional but somewhat vague.

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 description lacks enough context for an agent to confidently invoke the tool: it does not define what 'large-context recall' means in practice, what output to expect, how mode affects behavior, or how this evaluation relates to the many sibling evaluation tools.

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?

The schema provides no parameter descriptions, and the description only loosely maps 'N records' to n_records and 'queries them at the tail' to the evaluation behavior. The meanings of mode and top_k, and the effect of their defaults, are not explained.

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 a large-context recall scenario and states that it saves N records and queries them at the tail, which makes the core evaluation behavior clear. It is reasonably distinguishable from sibling memory_eval_* tools by the explicit 'long_context' tag mention.

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 gives only a subtle hint about reusing eval_harness scenarios tagged 'long_context', but does not explicitly say when to choose this tool over sibling evaluation tools such as memory_eval_recall or memory_eval_locomo. No clear use-case boundaries are provided.

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