memory_improve

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with 'Writes nothing itself' and 'Returns candidates only', which is meaningful for an agent that might otherwise assume aggregation also persists. It does not cover rate limits or cost of scanning up to 100 memories, so it adds context but not exhaustively.

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 output, then the workflow constraint, then the safety clarification. No filler or repetition.

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?

With no output schema, the description is responsible for describing the return, and it does so at a high level ('clustered proposal scaffold', 'candidates only'). Behavior, follow-up path, and read-only nature are all covered; only a slightly richer description of the scaffold shape would make it fully complete.

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 both the topic and limit parameters are already documented in the schema, including the default and cap for limit. The description adds no parameter-level detail beyond 'about a topic', so the baseline 3 applies.

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 and resource ('reflect over your memories about a topic') and names the concrete output ('clustered proposal scaffold for consolidated rules'). It is clearly distinguishable from read-only siblings like memory_search and the write sibling memory_store.

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?

Gives explicit workflow guidance: this returns candidates only, you review, then persist with memory_store. That routes the agent to the correct follow-up tool. It lacks a direct 'use memory_search instead if...' exclusion, so it stops short of full when-not coverage.

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