dedupe_memories

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

With no annotations, the description must disclose behavioral traits. It mentions merging and returning a count, but omits whether the operation is destructive, reversible, or requires confirmation. It also doesn't explain what 'near-duplicate traces' means or what happens to the merged traces.

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 with no filler. It front-loads the primary action and includes the return value, making every word informative.

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 the tool's simplicity (no params), the description covers the core action and return value. However, with no annotations or output schema, it leaves out important context like side effects or reversibility, making it only partially complete.

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 zero parameters and the schema is an empty object, so the baseline is 4. The description adds no param info, but none is needed since the tool takes no inputs. The description's mention of 'on demand' clarifies invocation context.

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 a specific action ('Merge') and resource ('near-duplicate traces'), and the return value ('returns how many duplicates were merged') adds specificity. This distinguishes it from sibling tools like 'cleanup_preview' or 'memory_audit'.

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 phrase 'on demand' implies manual usage, and the description conveys the core function, but it doesn't explicitly mention when to use this tool versus alternatives like 'forget' or 'restore'. No exclusions or prerequisites are provided.

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