RecallNest

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

No annotations provided, so description carries full burden. It successfully establishes persistence semantics ('durable', 'survive future windows') but lacks operational details: no mention of merge/update behavior (implied by canonicalKey parameter), failure modes, rate limits, or atomicity guarantees.

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?

Two sentences with zero waste. First sentence establishes action, trigger conditions, and durability requirement; second establishes exclusion criteria. Front-loaded with essential constraints.

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?

Adequate for 7-parameter tool with rich schema. Covers storage intent and durability semantics comprehensively. Minor gap: does not clarify upsert behavior suggested by canonicalKey parameter or success/failure return patterns (though no output schema exists).

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 coverage is 100%, establishing baseline 3. Description adds value by mapping concrete content examples (preferences, identity facts, etc.) to the category enum and text parameter, helping agents understand what constitutes valid input beyond raw schema definitions.

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?

Specific verb 'Store' + resource 'durable memory' + concrete content examples (preference, identity fact, project entity, pattern, solved case). Explicitly distinguishes durable storage from transient alternatives via sibling differentiation ('survive future windows').

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?

Explicit positive guidance ('when the user shares...') and negative constraint ('Do not use this for transient task state'). Clear when-to-use vs when-not-to-use boundaries implicitly reference sibling tools like brief_memory/checkpoint_session for transient needs.

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