memory_consolidate

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

No annotations, so the description carries the burden. It discloses that dry_run=true (default) only reports candidates, which is valuable. But it does not say what a non-dry-run merge does to the original memories, whether it is reversible, or what output is returned. Partial transparency.

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?

One sentence with the key operation first, then the safety default. No filler and the most decision-relevant information is front-loaded.

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?

Despite dry-run safety, a merge operation with no annotations, no output schema, and no description of what merging does to existing memories is incomplete. An agent cannot predict the consequences of dry_run=false or what the candidate report looks like.

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 schema documents threshold but not dry_run. The description compensates by explaining dry_run's meaning and default behavior, so the agent understands the safe mode. Threshold's meaning is inferable from vector similarity context and the schema already covers it.

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?

States the exact operation (find and merge near-duplicate memories), the criterion (vector similarity), and the default behavior (dry_run only reports candidates). Clearly distinct from memory_search/add/replace/remove by the consolidation goal.

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?

Implies use for deduplication via near-duplicate detection, and dry_run behavior is explained. However, there is no explicit when-to-use vs memory_replace/remove, no conditions for when consolidation is appropriate, and no exclusions.

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