Recall

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

The annotations show readOnlyHint=false on what is nominally a search, which would otherwise look contradictory; the description resolves this by disclosing the side effect: 'Returned memories are reinforced.' It also explains the retention/fade behavior that governs ranking, adding real behavioral context beyond the structured fields.

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 sentences, each earning its place: purpose, when-to-call, then ranking/side-effect mechanics. The most important action guidance is front-loaded and there is no filler.

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 4-parameter tool with no output schema, the description covers purpose, timing, ranking semantics, and the mutation side effect. It stops short of describing the shape or ordering of results, which an agent might want, but nothing essential for correct invocation is missing.

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 query, tags, limit, and since are all documented in the schema with defaults and formats. The description adds no parameter-level detail (e.g., how tags interact with query), 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?

The description names a specific verb and resource ('Search long-term memory') and clarifies the retrieval mechanism (hybrid BM25 + embeddings, weighted by retention). It distinguishes itself adequately from siblings like remember/forget/link, though it never explicitly contrasts with them.

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?

It states a clear trigger condition: 'Call it before answering questions about this user or project and when starting a task.' That is actionable usage guidance. It does not name when NOT to use it or point to a sibling alternative, which keeps it short of a 5.

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