memory_merge

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

The description clearly discloses the destructive nature (soft-deletion of sources) and the retention of snapshots and provenance, aligning with the destructiveHint=true annotation. It also highlights the dry_run safety mechanism.

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 flows logically from preview to apply. It avoids unnecessary detail and effectively conveys the core action.

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?

While the two-step process is clear, the description does not specify what the preview returns, how to handle errors or conflicts, or the role of the remaining parameters. This leaves gaps for an agent to invoke the tool effectively, especially without an output schema.

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 lists 8 parameters but the description only clarifies dry_run and proposal_token in the context of the workflow. It leaves target_id/source_ids inferred as the merge targets/sources, and omits any explanation for title, content, project, and namespace. With 0% schema description coverage, parameter semantics are largely undefined.

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 explicitly states the tool merges memory records, with a preview step and an apply step using a proposal token. It is distinct from sibling tools like add, update, delete, and search.

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?

It describes a two-step workflow: preview with dry_run, then apply with proposal_token. It also warns that source records are soft-deleted and originals retained, guiding safe usage. However, it does not compare to alternatives or specify when merge is preferred.

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