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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe read-only nature is covered. The description adds that it returns a 'no_evidence_available' kind when no evidence exists, and mentions the return structure, but does not disclose details like whether results are paginated or if there are rate limits. Since annotations cover the safety profile, the description adds moderate value, warranting a 3.

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 detailed but dense, covering purpose, modes, return types, and an example in a few sentences. It front-loads the core query capability and then provides mode-specific details. The inclusion of 'Added by CO 2026-05-30-022-003' is minor extra noise, but overall it's structured and efficient, earning a 4.

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 (three modes, two optional parameters, no output schema), the description is fairly complete: it explains each mode, the return format, and provides an example. It does not mention edge cases like whether co_id is required for touched_co or if agent_id is required for agent_autonomous, but the schema shows they are optional, so some ambiguity remains. Still, it covers most needed context, warranting a 4.

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 0%, so the description must compensate for parameter meanings. It does so by explaining the 'mode' parameter with three enumerated values and their semantics, plus indicating that 'co_id' and 'agent_id' are used with specific modes. The example call further clarifies usage, which is more than the schema alone provides, justifying a 4.

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 states the tool queries the 'CO-management decision log' with a specific verb ('Query') and resource, and distinguishes between three modes with concrete examples (touched_co, agent_autonomous, escalated). It also provides the return format, making its purpose unambiguous and distinct from siblings like introspection_system_change_graph.

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 gives clear context for when to use each mode, including what each mode returns (e.g., 'what decisions touched a CO', 'what is escalated and waiting on the operator'). It implicitly suggests that using mode is required and that co_id or agent_id are needed for certain modes, but does not explicitly state when not to use this tool versus alternatives, so a 4 is appropriate.

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