mnemos

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

Annotations indicate destructive, non-idempotent behavior affecting the open world. The description adds context that this performs 'decay' (TTL expiration), 'archival', and 'GC' (garbage collection), which explains what gets cleaned up. However, it fails to explain the non-idempotent nature (critical for retries) or quantify the destruction scope.

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?

Extremely concise at five words with zero redundancy. The list structure (decay, archival, and GC) efficiently communicates distinct operations. Slightly telegraphic; 'Run' is weaker than 'Execute' or 'Perform', and the sentence lacks contextual framing.

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?

Minimal but sufficient for a single-parameter tool with complete schema coverage and rich annotations. The destructive scope is hinted via operation types (GC, archival), but the non-idempotent risk—unusual for maintenance tasks—warrants explicit warning given the optional 'all projects' scope.

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 parameter 'project_id' is fully documented as 'Project scope (empty = all)'. The description adds no additional parameter semantics, but meets the baseline expectation when the schema is self-documenting.

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?

Description uses specific verb 'Run' and identifies three distinct maintenance operations (decay, archival, GC), clearly distinguishing this from CRUD siblings like mnemos_store and mnemos_get. However, 'GC' is jargon and 'decay' assumes domain knowledge of the Mnemos system.

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?

Provides no explicit guidance on when to invoke this tool versus alternatives. No mention of scheduling, prerequisites, or conditions like 'run when storage threshold exceeded' that would help an agent decide to use this over other cleanup strategies.

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