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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds useful return-content context ("decision-time facts and evidence status"), which matters because there is no output schema, but it says nothing about pagination behavior for the limit parameter or what happens when a subject has no decisions.

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?

Three short sentences with zero filler: purpose first, then return payload, then the sibling hand-off. Every sentence carries distinct information and the most decision-relevant content is 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?

For a five-parameter read tool with no output schema and 40% schema coverage, the description covers purpose and return shape but omits parameter-level guidance and behavior with zero required arguments. Annotations carry the safety profile, so the remaining gap is moderate rather than critical, but an agent still cannot tell from the description how to page or how to combine subject_id with source_scope_id.

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 only 40%, and the description never names limit, subject_id, subject_type, or source_scope_id. It does implicitly clarify the dual addressing scheme (query by Graph entity ID versus source subject), which helps distinguish subject_entity_id from subject_id, but leaves the limit cap and the scope/type filtering semantics entirely to 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 states a specific verb and resource ("Read decisions for any Graph entity ID or source subject") and distinguishes itself from the similarly named graph_decision_detail. It is clear enough to select without opening the schema, though the phrase "decision lineage" in the name versus "read decisions" in the text leaves a slight ambiguity about whether lineage edges or decision records are returned.

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?

It explicitly routes one alternative: "Use graph_decision_detail for captured warnings," giving an agent a concrete condition for choosing the sibling. It stops short of stating when not to use this tool (e.g. use graph_record_decision to write, or graph_precedent for cross-entity patterns), so the coverage of alternatives is partial rather than exhaustive.

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