Pending memories & corrections

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

The annotations already declare readOnlyHint and idempotentHint, so the description need not repeat them. It adds valuable context about anti-poisoning and the requirement for user confirmation, which is additional behavioral guidance beyond the annotations and helps the agent understand the safety implications.

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 concise, uses a clear numbered list for the two types, and includes a direct trigger instruction. No unnecessary fluff, and the structure aids readability.

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 provides enough context to call the tool correctly: when to call it, what it lists, and how to handle the results. It also mentions the anti-poisoning rule. Since an output schema exists (though not shown), explaining return values is not required. The tool is fully specified for an agent to use.

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?

There are no parameters, so the schema fully covers them. The description adds no parameter details (irrelevant here). Baseline score for zero parameters is 4.

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 clearly states the tool lists automatically extracted but unconfirmed items, and distinguishes two types (memories and corrections) with explicit handling tools. This is a specific verb ('list') and specific resource ('pending memories & corrections'), and it differentiates from siblings like memory_recall by emphasizing the unconfirmed nature.

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 explicitly says to call after memory_extract/memory_capture and provides the exact follow-up tools (memory_confirm/reject, correction_confirm/reject). It also warns against using this for recall until confirmation, which clarifies when not to use it and when to use alternatives like memory_recall.

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