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

No annotations are provided, so the description carries the full behavioral burden. It discloses important behavior (no-op with reason when graph isn't enabled; predicate must be registered) but omits other traits like idempotency, permission requirements, and error semantics. An output schema exists, so return values need not be explained.

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 front-loaded sentences with no wasted words. Purpose first, then a key behavioral caveat (no-op), then usage guidance and a prerequisite pointer. Every sentence earns its place.

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 a 6-parameter write tool with an output schema and no annotations, the description covers purpose, usage, no-op behavior, and the predicate registration requirement. It does not mention the weight parameter or the agent override, but these are documented in the schema. Complete enough for correct invocation.

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 high (83%), so baseline is 3. The description adds meaning beyond the schema by clarifying that predicate must be a registered link type and by giving an example triple ('alice -> works_on -> teamshared') that maps the subject/predicate/object roles. It does not cover the weight parameter, but otherwise it enhances parameter understanding.

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 (Record) and resource (explicit relationship in the org-scoped graph store), and distinguishes it from vector recall by saying it is for structured facts that vector recall would obscure. An agent can tell this is the graph-writing tool, not a read or vector tool.

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?

Provides a clear when-to-use condition: when you learn a structured fact that vector recall would obscure. Also notes a prerequisite (predicate must be registered, see memory_ontology_list) and a no-op condition when the graph isn't enabled. No explicit when-not-to-use or named alternative write tool, but context is clear.

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