memoryguard_memory_merge_safe_preview

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

With no annotations provided, the description fully carries the behavioral disclosure burden and does so explicitly: 'does not write transactions, decisions, undo, or idempotency records' and 'There is no force or bypass.' It also names the exact information returned, giving the agent a clear model of the tool's safe, side-effect-free behavior. This is exceptional transparency for a zero-annotation tool.

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 two tightly written sentences with no filler. It front-loads the most important fact ('Read-only preflight'), then packs scope, outputs, and exclusions into a compact sequence. Every sentence earns its place and the conciseness aids quick agent parsing.

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?

For a tool with no output schema, the description lists the categories of returned data (revisions, policies, priorities, relation safety), which helps. However, all five parameters are optional, and the description does not explain which combinations are valid or what happens when only some IDs are supplied. The ambiguity around atom IDs versus memory IDs also leaves an incomplete picture for an agent deciding what to pass.

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 80%, so the schema already documents most parameters. The description adds minimal parameter-level meaning beyond the schema; it references a 'canonical/duplicate atom pair' but does not explain the relationship between the atom_id and memory_id parameters, which is a source of potential confusion. Baseline 3 is appropriate because the schema does the heavy lifting, but the description does not enrich parameter understanding.

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 opens with 'Read-only preflight for memoryguard_memory_merge_safe', making the verb, resource, and role immediately clear. It explicitly says what it resolves ('one explicit canonical/duplicate atom pair'), what it returns ('current atom revisions, policies, priorities, and relation safety'), and what it does not do ('does not write transactions...'). This clearly distinguishes it from the merge_safe sibling and from write-oriented memory tools.

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 clearly frames this as a preflight check for memoryguard_memory_merge_safe, so an agent can infer it should be used before executing a merge to inspect expected effects. It also states there is 'no force or bypass', setting expectations that this only reports safe preconditions. It does not explicitly name alternatives or say 'use memoryguard_memory_merge_safe when you intend to write', but the read-only/write contrast makes that implication strong enough.

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