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

Annotations already declare readOnlyHint=true, but the description goes well beyond that: it discloses that edges are returned in separate blocks by relationship_class, that every edge carries an inline 'does_not_mean' caveat, and that empty results are true negatives, not errors. This is exactly the kind of nuanced behavior an agent needs to interpret results correctly.

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 front-loaded with the core question and densely packed with necessary caveats, examples, and scoping details. Every sentence carries meaning, and the length is justified by the semantic nuance of the relationship graph.

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 that an output schema exists, the description does not need to explain return formatting. It covers current data population, how to obtain valid record_id values, the meaning of relationship classes, the built-in caveats, and the true-negative semantics, so an agent has enough to call and interpret the tool correctly.

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 100%, and the schema already documents include_computed and include_unresolved, including a strong warning about the latter. The description mainly adds contextual advice about sourcing record_id from archive_search or colour_card, but does not add significant meaning beyond the schema.

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 names a specific operation: one-hop lookup over Colour Memory's stored relationship graph for an archive record. It explains what the tool returns and even separates edge classes, but it never explicitly distinguishes itself from the closely named sibling tool why_connected, so it misses the sibling-differentiation bar for a 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?

Provides strong context for when to use it: it is scoped to archive record relationships, notes current data population, tells users where to get record_id values, and warns that an empty result is a true negative. It does not explicitly state when not to use it or name alternative tools, so exclusions are missing.

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