memoryguard_rule_merge_safe_preview

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It explicitly states the tool is read-only, lists several record types it does not write, and explains that composer/pair safety still governs mergeability. This gives an agent strong expectations about side effects and guarantees.

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?

Three focused sentences deliver the core purpose, behavioral guarantees, and key caveat without wasted words. The most important information is front-loaded: 'Read-only preflight' appears immediately.

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 no output schema and no annotations, so the description must cover behavior and expected results well; it does, mentioning current definition revisions and pair safety. However, it does not describe the exact return structure or clarify whether workspace is required for resolution, leaving minor gaps for an agent.

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 echoes the same canonical/duplicate source and definition ID concepts rather than adding deeper semantics, and it does not explain the workspace parameter, which is the one undocumented field.

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_rule_merge_safe,' naming a specific verb, resource, and operation. It clearly distinguishes itself from the actual merge tool by stating it resolves IDs, returns revisions and pair safety, and does not write anything.

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 step for memoryguard_rule_merge_safe, giving strong context on when to invoke it. It does not explicitly name alternatives like the actual merge command, but 'does not write transactions...' and 'no force or bypass' effectively communicate that this is not a substitute for performing the merge.

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