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

Annotations only say readOnlyHint=false; the description adds substantial context an agent could not infer: it is owner-scoped, it derives from metadata (who-sent-to-whom, thread membership) rather than message bodies, and therefore does not weaken E2EE. It does not say whether an existing graph is replaced or merged, or what a rebuild costs on large corpora.

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 compact sentences, front-loaded with the action and return value, then sequencing, then the privacy guarantee. Dense but every clause carries information; the parenthetical counts could arguably be trimmed.

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?

No output schema exists, and the description compensates by stating the return shape (counts of parties/mentions/edges). For a rebuild-style mutation with no annotations beyond readOnlyHint=false, the remaining gap is whether prior graph state is destroyed and any runtime/scale expectations.

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% and the single max_docs parameter already documents its range and default. The description adds nothing about the cap or tuning guidance, so the schema carries the full load — baseline 3.

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: '(Re)build the USER'S OWN knowledge graph from their indexed data', and adds what it returns (counts of parties/mentions/edges). It is clearly distinguishable from the read-only graph siblings (overview/neighbors/timeline) because it names them as consumers of its output.

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?

Explicitly prescribes timing: 'Run this first, or after new data has been ingested, so mRAG_graph_overview/neighbors/timeline reflect the latest.' That names both the alternatives and the condition that selects this tool over them.

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