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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds non-obvious behavior beyond that: results are hashed identifiers only, account scope is server-enforced and not settable, and it enumerates the returned fields (node_type, name_hash, relationships, chunk_ids, timestamps). It stops short of describing pagination or result-size behavior.

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?

Front-loaded purpose in the first two sentences, then a compact plan skeleton, then the enumerated vocabularies, then the scope caveat. The code block earns its length because the schema points readers to it for enum values.

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 nested-plan query tool with no output schema, the description supplies the return field list, the full allowed-value vocabularies, numeric bounds, and the server-enforced scope constraint. Nothing an agent needs in order to construct a valid plan is left unstated.

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?

The schema explicitly defers to the description for allowed values, and the description delivers them: the full node_type vocabulary, the ten valid relationship values, the direction enum, ISO 8601 temporal bounds, limit <= 200, and include_neighbours_depth 0-5. With additionalProperties true and zero enums in the schema itself, this text is the authoritative source of parameter meaning rather than a restatement.

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+resource ("Execute a structured query plan over your encrypted knowledge graph") and immediately declares the output scope ("STRUCTURE ONLY ... never content"), which is exactly what separates it from the sibling query_memory_content. An agent can distinguish it from the *content tools without opening a schema.

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 phrase "Returns STRUCTURE ONLY ... never content" functions as an implicit when-to-use/when-not rule and routes the agent toward the content-returning sibling for actual text. It also states an operational precondition the caller cannot override ("Account scope is enforced server-side; it cannot be set from the plan"), but it never names the alternative tool explicitly.

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