mnemos

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

The description fails to disclose the destructive, non-idempotent, and non-read-only nature of the operation. The word 'Get' conventionally implies safe retrieval, which contradicts the destructiveHint: true and readOnlyHint: false annotations.

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 extremely concise at only four words, with the action verb front-loaded. However, given the tool's destructive complexity, this brevity constitutes under-specification rather than efficient communication.

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 having complex annotations (destructive, open-world, non-idempotent) and no output schema, the four-word description provides no explanation of side effects, return values, or behavioral constraints, making it dangerously incomplete.

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?

With 100% schema coverage, the description meets the baseline by mentioning 'ID' which aligns with the documented 'id' parameter, but adds no additional semantic context like ID format, examples, or validation rules beyond the schema.

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 states the basic action (getting a memory) and specificity (by ID), but uses the ambiguous verb 'Get' which conventionally implies safe read-only retrieval, failing to capture the destructive nature revealed in annotations.

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?

No guidance provided on when to use this versus mnemos_search or other siblings, nor any warnings about the destructive behavior despite the destructiveHint annotation.

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