memory_save

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

With no annotations, the description carries the full burden. It does disclose real behavior beyond the name – auto-chunking, embedding for semantic recall, and the shared cross-agent store – which is genuinely useful. But it says nothing about deduplication, overwrite semantics, permissions, or what identifier is returned for later update/delete by the sibling tools.

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?

Three short sentences, front-loaded with the action and destination, then the mechanism, then the usage cue. No filler or redundancy.

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 no-annotation, no-output-schema mutation tool it covers the essentials (what it stores, where, how it is indexed). It omits the practical follow-up information an agent needs in a 15-tool memory suite – the returned handle and whether repeated saves overwrite or duplicate.

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 100%, so the schema already documents all four parameters, including defaults for scope and examples for source. The description adds no syntax, format, or constraint detail beyond what the schema provides, making the baseline 3 appropriate.

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?

States a specific verb (Save) and resource (a memory) and enumerates the content categories it accepts, plus the destination ('shared local store that both Codex and Claude read'). It does not differentiate itself from siblings like memory_update or handoff_save, which could be confused for similar write operations.

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?

'Use for durable info worth recalling' gives a positive usage condition but is fuzzy and names no alternatives or exclusions. An agent still has to infer why it would pick memory_save over handoff_save or memory_update.

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