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

Even with readOnlyHint=true, the description goes far beyond the annotation by explaining that results are separated by relationship_class to prevent mistaking computed distance for historical assertion, that every edge carries an inline 'does_not_mean' caveat, and that missing relationships are true negatives. It also discloses the current population state (348 Wada plates). This is rich, honesty-promoting behavioral disclosure.

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?

The description is dense but every sentence earns its place: framing question, population context, relationship-class distinction, caveat behavior, true-negative semantics, and input source guidance. It is front-loaded with the core question and strongly structured for agent comprehension.

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 the tool's complexity, the output schema, and the annotations, the description covers everything an agent needs to call it correctly: what the graph contains, how relationship classes are separated, what caveats accompany edges, how to interpret empty results, and where to obtain valid IDs. No critical context is missing.

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 already covers all three parameters at 100%, so the baseline is 3. The description adds meaningful context for record_id (stating its source) and for include_computed by clarifying what 'computed' relationships mean via DETERMINISTIC_STRUCTURAL. include_unresolved gets no description-level elaboration, but the schema carries its own explanation.

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 clearly states a specific verb and resource: a one-hop lookup over Colour Memory's stored relationship graph, returning edges grouped by relationship_class. It gives concrete examples of SOURCE_ASSERTED and DETERMINISTIC_STRUCTURAL relationships, which sharply defines the tool's job. However, it does not explicitly distinguish itself from sibling tools like why_connected, so it stops short of a perfect 5.

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 description gives clear usage context: this is a one-hop graph lookup, and it explicitly warns that an empty result is a true negative, not an error. It also tells the caller where to get valid record_id values (archive_search or colour_card). It does not name alternatives or state when not to use this tool, so it lacks explicit exclusions.

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