memora

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully explains the return structure ('Dictionary with count and list of events') and introduces the 'unconsumed' event state concept, but lacks critical details about side effects, rate limiting, authentication requirements, or how events are generated in the memory system.

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 uses a standard docstring format with clear Args and Returns sections. The first sentence effectively front-loads the purpose. However, the Returns description is minimally verbose and could be more specific about the event structure, though this is partially mitigated by the existence of an output schema.

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 description adequately covers the three parameters given zero schema coverage, it lacks context about the memory event system itself—what generates these events, their lifecycle, or how they relate to the broader memory toolset. For a tool with no annotations and low schema coverage, additional conceptual context would strengthen agent usage.

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?

Given the schema has 0% description coverage, the Args section provides excellent compensation by documenting all three parameters: since_timestamp includes the ISO format requirement, tags_filter includes a concrete example (['shared-cache']), and unconsumed_only clarifies its default value. This adds substantial meaning absent from the structured 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 clearly states the tool 'Poll[s] for memory events' with a concrete example ('shared-cache notifications'), establishing the verb and resource. However, it fails to explicitly distinguish this read operation from the sibling tool 'memory_events_clear', which could cause confusion about which tool handles event retrieval versus deletion.

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 provides no guidance on when to use this tool versus alternatives, nor does it explain the event consumption lifecycle (e.g., whether polling marks events as consumed or how unconsumed_only interacts with system state). There is no mention of prerequisites or polling frequency recommendations.

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