compare_memories

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

No annotations are provided, so the description carries the full burden. It does not disclose whether the tool is read-only, whether it modifies memories, what happens on invalid IDs, or how the verdict is computed. It only describes the output, not the behavior or side effects.

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 sentence, front-loaded with the key action ('Compare two memories'), and includes necessary details about outputs and purpose. The reference to Johnson et al. (1993) is extra but does not detract from clarity.

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 simple tool with no annotations and no output schema, the description covers the core function and outputs. However, it omits behavioral details like read-only nature, error handling, or how to interpret the verdict, leaving some gaps for an AI 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?

The schema provides only parameter names (id_a, id_b) with no descriptions. The description's phrase 'two memories' clarifies that these are memory identifiers. While it doesn't specify the exact format or whether the order matters, it adds enough meaning for a two-parameter tool.

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 compares two memories and specifies the outputs: token overlap, shared cues, and a verdict (duplicate/conflict/distinct). It is specific and understandable, though it does not explicitly differentiate from sibling tools like similarity_report or dedupe_memories.

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 gives a purpose ('source monitoring and schema integration') which implies when it might be useful, but it lacks explicit guidance on when to use this tool versus alternatives or any exclusions. It does not name alternatives or describe specific use cases.

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