memory_dedupe

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It clearly states that commit=True triggers destructive consolidation, while the default mode is read-only. This gives the agent essential safety context. A minor gap is not describing what happens to the original memory entries post-consolidation.

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 only three sentences, all dense with useful information. No wasted words. The first sentence states the core purpose, the second adds technical detail, and the third provides critical safety caveat. Excellent front-loading.

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 there is an output schema, the description does not need to explain return values. There are only 3 parameters with 0% schema coverage, so the description partially compensates for 2 out of 3 parameters. It lacks explanation of sample_limit and what happens after commit=True (e.g., whether the return still shows groups). Overall adequate but not fully comprehensive.

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%, so the description must compensate. It explains that bank specifies the memory bank to scan (default 'infra'), and that commit controls whether to perform destructive consolidation. However, sample_limit (default 500) is mentioned only in schema; the description does not clarify its purpose (e.g., limits number of duplicates considered or max memory entries sampled).

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 that the tool finds duplicate/over-fragmented memories and proposes merging. It specifies the input (memory bank), the detection methods (chunk_id collisions and normalized-text duplicates), and the output (proposed groups). This distinguishes it well from siblings like memory_ingest_url or memory_recall.

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 explicitly says that by default the tool is read-only (detect only), and that setting commit=True performs consolidation which is destructive. This provides clear guidance on when to use it safely. However, it could be improved by mentioning when to prefer this over simply recalling memories or other alternatives.

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