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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description goes further by defining the fidelity taxonomy (resolved = stored and keyed, derived = reconstructed at read time and a judgement you own, absent = named but not held), which is genuine behavioral context an agent needs to interpret results. It does not say anything about cost or pagination, but for a read-only graph it is sufficient.

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 with the imperative call-to-action, then the payload, then the narrow-behavior note and the NEXT pointer. Dense but every clause carries information. One overly long sentence in the middle slightly hurts scanability.

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 no output schema, the description must characterize the return value, and it does: nodes, crossings, endpoint-per-crossing, and a fidelity label on every node and edge, plus the meaning of each fidelity. An agent knows what it will get and what to do next.

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 baseline is 3, but the description adds real meaning: it explains that the optional arguments narrow to one node or one fidelity, and it defines the three fidelity values far beyond the schema's bare "resolved, derived or absent". That interpretive layer is what the schema omits.

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 (Returns) and resource (the primitives this platform resolves), then enumerates the primitives, the crossings, the endpoint mapping, and the fidelity metadata. It also names the follow-on sibling (get_research_curriculum), so an agent can place it without opening any 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?

"CALL THIS BEFORE PLANNING A MULTI-STEP QUERY" gives an explicit triggering condition, and "NEXT: get_research_curriculum" names the alternative/complement plus the sequencing. There is no explicit when-not-to-use (e.g. for single-lookup queries), which keeps it from a 5.

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