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

Annotations already establish the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavior beyond that: it describes the two possible return shapes ({kind: "evidenced", value, chain} or {kind: "no_evidence_available", reason}) and notes the inclusion of confidence, threshold, outcome, accountability, and PR links. 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 dense and front-loaded with purpose and modes, but it is a long single block with redundant return statements ('Returns: The recorded change-order decisions' repeats earlier content) and a placeholder example that uses "<mode>" rather than a concrete value. It could be tightened without losing value.

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 read-only query tool with no output schema, the description covers the essential context: all three modes, associated parameters, return envelope variants, and provenance note. Minor gaps remain, such as what happens if both co_id and agent_id are supplied or whether mode values constrain required parameters, but overall the tool is well-specified.

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%, so the description must compensate—and it does. It explains when to supply co_id versus agent_id and maps each mode to the relevant parameter. The schema only lists the enum and maxLength, so the description adds meaningful usage semantics beyond the structured fields.

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?

Description explicitly states the tool 'Query the CO-management decision log' and details what it returns: every change-order operation an agent scored or actuated. It clearly distinguishes itself from sibling tools by naming the specific domain (CO-management) and the three query modes.

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 clearly given through mode-specific instructions: mode="touched_co" with co_id, mode="agent_autonomous" with agent_id, mode="escalated" for waiting items. It does not explicitly state when not to use the tool or name alternatives, but the mode examples provide clear situational guidance.

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