memory_consolidation_candidates

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

With no annotations, the description carries the burden. It reveals that this is a read-only candidate-finding operation ('read the clusters... commit it via memory_consolidate'), and it specifies the return format: `{count, clusters: [{cohesion, size, members}]}`. It also explains the effect of `min_cohesion`. It does not mention any side effects, but the read-only nature is implied clearly.

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 reasonably concise and well-structured, using an 'Args' and 'Returns' breakdown. The first sentence includes a bit of colorful language ('the same thing phrased five ways') but it is not excessive. It conveys the core purpose and usage in a compact form. It loses one point for the slightly informal metaphor that adds little practical information.

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 tool has 8 parameters and no annotations, and the description covers only a few of them. While the central workflow is clear, the unexplained parameters like `top_k`, `max_clusters`, `min_cluster_size`, `tags`, and `sources` could affect results significantly. The return format is provided, but for a tool with this complexity, a bit more parameter context would be needed to be fully 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?

Schema description coverage is 0%, so the description must compensate. It explains `query` and `episode` as anchoring options, and `min_cohesion` with a concrete example ('raise to flag only near-duplicates'). However, it leaves five parameters unexplained (`tags`, `top_k`, `sources`, `max_clusters`, `min_cluster_size`), so the agent cannot fully understand the tool's configurability without additional inference.

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's function: 'Find clusters of near-duplicate memories ripe for consolidation.' It uses a specific verb ('find'), a clear resource ('clusters of near-duplicate memories'), and differentiates from siblings like memory_consolidate (which actually commits the consolidation) and memory_search (which searches broadly). The purpose is unambiguous.

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 a usage pattern: 'Anchor with a `query` (topic-driven) or an `episode` id (session-driven); read the clusters, synthesise one canonical note, then commit it via `memory_consolidate`.' This tells the agent when and how to use the tool and explicitly connects it to the next step. It does not explicitly state when not to use it, but the guidance is sufficient for common scenarios.

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