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

Despite having no annotations, the tool definition provides meaningful behavioral details: depth describes the addition of an expansion block with hop annotations, and limit/maxNodes explicitly distinguish per-level bounds vs whole-expansion ceilings. The description itself mentions 'governed' predicates and output annotations, which adds context about data quality and result structure. However, it does not state whether the operation is read-only or if any authentication/permission constraints apply, leaving some burden unmet.

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 main description is a single sentence that immediately conveys the core purpose and key output attributes, placing the most important information upfront. The parameter descriptions are verbose but densely useful, with no filler. The structure is clean and front-loaded.

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?

The tool has 13 parameters, no annotations, and no output schema, so the description must carry more weight. The parameter descriptions explain key behaviors (expansion, limits), but the overall response shape is under-specified: the phrase 'with source, truth state, confidence, and hop annotations' hints at the output, but it remains unclear whether results are a flat list, nested graph, or node/edge blocks. Error scenarios and default behavior when no entity is given are also not addressed.

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 85% (11 of 13 parameters have descriptions), so the baseline is 3. The main description does not add much parameter-level meaning; it echoes 'truth state' and 'confidence' but does not clarify the 'truthStates' or 'minimumConfidence' parameters, both of which lack schema descriptions. Some parameter descriptions (depth, limit, maxNodes) are rich and provide practical context, but this is primarily from the schema, not the tool description.

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 uses a specific verb ('Find') and resource ('entities connected through governed graph predicates') and further defines the result by naming source, truth state, confidence, and hop annotations. This distinguishes it from sibling tools like get_entity, search_entities, and find_potential_customers, which target single entities, free-text search, or specialized relationships.

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 main description does not explicitly compare this tool to alternatives, but the name and phrase 'connected through governed graph predicates' imply graph traversal as the intended use. Parameter descriptions in the schema (e.g., depth's example of fetching containment chains in one call) hint at use cases, but there is no explicit when-to-use or when-not-to-use guidance relative to similar siblings like query_knowledge_graph or traverse_relationships.

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