add_memory

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose a meaningful trait beyond the schema: that sector defaults to an automatic classification the caller can override, and that metadata 'type' improves later filtering. However, it says nothing about deduplication/uniqueness, permissions, or side effects, which matter for a write tool with no annotation coverage.

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?

Front-loaded with the core action, then a compact run-through of each parameter. No filler sentences, and the per-parameter notes are dense with useful guidance rather than padding.

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?

An output schema exists, so return values need not be described. With 0% schema description coverage across four params, the description compensates for all of them meaningfully. The main remaining gap is the absence of any durability/duplication or permission behavior for a write operation lacking annotations.

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 0%, so the description must carry parameter meaning, and it does: content is scoped to "one self-contained fact, with absolute dates," sector enumerates the five classification values as an override, and metadata 'type' is given concrete examples (system_info, preference, decision, troubleshooting). Only 'tags' is left with bare "optional" and no semantic guidance.

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?

Clear specific verb+resource: "Store a new memory." The action is unambiguous and easily distinguished from siblings like get_memory, delete_memory, search_memories, and reinforce_memory. It does not explicitly name or contrast with any sibling, so it stops short of the top band.

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?

Usage is implied by the purpose (use this to persist a new fact), but there is no explicit when-to-use/when-not guidance and no routing to alternatives. Notably it does not address when to add a fresh memory versus reinforcing an existing one (reinforce_memory), leaving a real ambiguity for the agent.

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