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

Despite annotations providing readOnlyHint=true, the description adds substantial behavioral context: it details the ranking logic (direct neighbors before co-citation siblings, sitering_count as tie-break), explains the relation field values, and describes the output as a ready-ranked list. No contradiction with annotations.

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 well-structured with bullet points and a clear hierarchy, but it is somewhat verbose. However, every sentence adds value, and the key question is front-loaded. A minor reduction in explanation could improve conciseness without losing meaning.

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 moderate complexity (3 parameters, no output schema), the description is comprehensive. It explains the output format (ranked list with relation field), the ranking logic, and the _meta.note for empty results. No output schema is needed as the description covers return value semantics.

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 0%, but the description compensates fully. It provides example formats for the id parameter (HR-2024-1016-A, Rt-1979-524), lists allowed values for instanser (hoyesterett, lagmannsrett, tingrett, alle), and clarifies the behavior when results are empty.

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 opens with a specific question ('Hvilke dommer henger sammen med <id>?') and clearly defines the tool as finding precedent neighbors via citation graph. It explicitly distinguishes itself from sibling tools like search_decisions (topic-based) and find_decisions_applying_law (section-based).

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 explicitly states when to use this tool (e.g., user asks for similar/related decisions, mapping a doctrine) and when the alternatives are insufficient. It also explains the meaning of an empty result and directs the user to _meta.note.

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