memo_rerank

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

The description states 'Read-only,' aligning with annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false). It adds behavioral context beyond annotations, explaining that the tool reorders and subsets hits, and that `top_n` limits the output.

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?

The description is three sentences, front-loaded with purpose. Every sentence adds value: purpose, read-only declaration, usage context, and parameter hint. No unnecessary words.

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?

Given the tool has 4 parameters, no schema descriptions, but an output schema exists, the description adequately explains the tool's role in a workflow. However, it lacks detail on the expected format of `hits` and the return structure, making it somewhat incomplete.

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 0% schema description coverage, the description must compensate but only mentions `top_n` ('limits the returned list'). Other parameters (hits, query, body_chars) are not described, leaving the agent without crucial semantic information.

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?

The description clearly states the tool's purpose: 'Rerank candidate memory hits for a query.' It specifies the verb (rerank) and resource (candidate memory hits), and distinguishes it from siblings like memo_search by indicating it is used after retrieval.

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?

The description provides explicit context: 'Use after memo_search or another retrieval source when you already have candidate hit dictionaries and need the most relevant subset ordered for answer synthesis.' This clearly indicates when to use, though it does not explicitly list when not to use.

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