memory_verify_integrity

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

With no annotations provided, the description carries the full burden of disclosing behavior. It correctly declares the tool as 'Read-only', which is critical for an agent to know it is safe to invoke. However, it does not disclose what 'integrity' means (e.g., consistency checks, corruption detection), what 'bounded offending ids' implies (e.g., a limit on results), or any other behavioral traits such as cost or side effects, leaving room for ambiguity.

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, concise sentence that conveys the core purpose and a key behavioral trait ('Read-only') without any wasted words. It is front-loaded with the most critical information and easily digestible by an agent.

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?

Given that the tool has no parameters and a very specific purpose, the description covers the basics. However, the presence of an output schema is noted in the context, and the description does not hint at what the output contains beyond 'bounded offending ids', leaving the agent to rely solely on the output schema for understanding return values. For a diagnostic tool among many similar siblings, more context on what kind of integrity issue is detected would improve completeness.

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 input schema has zero parameters and is 100% covered by the schema definition itself. Since there are no parameters to document, the description cannot add value beyond the schema; therefore, the baseline 4 is appropriate, but the clear description of the tool's action ('verify integrity') and output characteristic ('bounded offending ids') effectively communicates what the no-parameter invocation does, earning a 5.

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 verb ('verify') and resource ('embedding integrity'), and the phrase 'bounded offending ids' adds specificity about what the reader can expect from the output, distinguishing it as a diagnostic tool. It does not, however, elaborate on what aspect of integrity is checked, and with many sibling tools like memory_find_duplicates and memory_detect_supersessions also performing diagnostics, the distinction is only moderate.

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 no guidance on when to use this tool versus any of the many sibling tools. The phrase 'Read-only embedding integrity doctor' implies a safe diagnostic context, but there are no explicit when-to-use, when-not-to-use, or alternative suggestions, leaving the agent to guess its role among over 40 siblings.

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