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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so 'Read-only' restates structured data rather than adding to it. The description does add the return shape and the cross-parameter precondition, but leaves important behavior unstated: whether multiple filters are ANDed or ORed, and whether results are ordered or truncated beyond 'limit'.

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: purpose first, safety/precondition second, return value third. No filler, no repetition, and the most decision-relevant content is front-loaded.

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 full schema coverage, rich annotations, and an output schema, the description need not explain field formats or return structure, and it does supply the key precondition. The remaining gap is filter-combination semantics for a tool with five optional parameters, which an agent would still have to guess.

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%, so 3 is the floor, and the description earns above it by surfacing the cross-parameter constraint that at least one of memory_id, tags, or collection must be supplied — a rule the schema cannot express because it uses no anyOf and no required list. It adds nothing extra about relation_type or limit, which the schema already documents.

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 gives a specific verb and resource ('Discover related memories') plus three concrete discovery mechanisms (links, shared tags, collection membership), which implicitly separates it from memory_search (query-based) and memory_list (enumeration). It never names a sibling explicitly, so an agent must infer the boundary rather than being told it.

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 statement 'At least one of memory_id, tags, or collection is required' is a genuine precondition that tells the agent when the call is valid, which is useful given the schema declares no required properties. However, there is no guidance on when to prefer this over memory_search, memory_recall, or memory_list, so the agent gets a validity rule but no routing rule.

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