stats

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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds actions like 'maintenance' and 'audit_leak' but does not warn about potential side effects (e.g., rebuilding indices may be resource-intensive or destructive). Given the annotation coverage, the description provides moderate additional context but misses important behavioral notes for maintenance.

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 moderately concise but has a cluttered structure with a bullet list of actions and maintenance ops. The front-loading of the overall purpose is good, but the redundant 'ACTIONS:' section and trailing 'Args:' list could be streamlined. It is not overly verbose but could be more efficient.

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 complexity (multiple actions, 4 parameters, no schema descriptions), the description covers the main actions and parameters but lacks details on return values (output schema exists but is not referenced) and potential side effects of maintenance. It is adequate but leaves gaps that could mislead an agent.

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. It lists the action, namespace, maintenance_op, and max_rids, and briefly explains some (e.g., 'max candidate rids to inspect'). However, it does not clarify the format or semantics of namespace, and the maintenance_op values are listed but not explained. The description adds some value but is incomplete for a 4-parameter tool with no schema descriptions.

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 lists multiple actions (stats, health, weights, maintenance, audit_leak, skill_outcomes) and states 'Engine statistics, health check, learned weights, maintenance ops, privacy/leak audit, and skill substrate counts.' This clearly identifies the tool as a multi-purpose diagnostics utility. However, the primary purpose is somewhat diluted by the variety, and the title is null, which slightly reduces clarity.

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 provides no explicit guidance on when to use this tool versus its siblings (e.g., memory, recall, task). The actions imply different use cases, but there are no when-to-use or when-not-to-use statements, nor any comparison to alternative tools. This leaves the agent without clear decision criteria.

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