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 covered and the bar is lower. The description adds that matching spans entity types and combines structured filters with text search, but says nothing about how "similar" is determined, ranking/relevance order, or whether `limit` truncates results — meaningful gaps for a search tool.

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?

Two short sentences, front-loaded with the core action, with no filler or repetition. The second sentence is compressed to the point of being cryptic ("query decision lineage"), but nothing is wasted.

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 19-parameter, all-optional search tool with 11% schema coverage and no output schema, the description is far too thin — it neither groups nor explains the filter families the agent must reason about. an agent could call it, but would have to guess at most of the 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 description coverage is only 11% (just `query` and `decision_type`), and the description compensates with only the generic phrase "structured filters and text search." It never explains the metric pairing (metric_key with min_metric/max_metric), the context pairing (context_key with context_value), the distinction between subject_type and subject_entity_id, or the outcome/outcome_category and warning_* filter families.

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?

"Find similar past decisions across entity types" gives a concrete verb (find) and resource (past decisions), and the second sentence specifies the two query modes (structured filters plus text search). It does not, however, distinguish this from close siblings such as graph_decision_detail or graph_decision_lineage, and "query decision lineage" actually blurs the boundary with the latter.

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?

Usage context is only implied by the word "precedent" and "similar past decisions"; there is no explicit statement of when to pick this over graph_decision_detail, graph_decision_lineage, graph_ask_question, or graph_entities. No preconditions, no exclusions, and no mention of what happens when no filters are supplied (all 19 params are optional).

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