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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is provided. The description adds useful non-obvious behavioral constraints: it mandates a specific start tag ('begin'), uses a multi-step stateful workflow with what appears to be a status gate for final wisdom, and requires the previousJourney string to be passed back. These are important behavioral details beyond the 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 compact and front-loaded: it states the purpose, then immediately gives the hardest truths (start with begin, do not finalize until WISDOM_READY) and a tag reference. The tag list is long but justifies the structure— an agent needs that vocabulary order. It does not contain redundant or mercenary sentences.

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?

This is an unusually stateful tool with a complex workflow, and the description covers the key runtime requirements: the mandatory first action, the stage-series progression, the status gate, and the previousJourney handoff. With an output schema present and full input parameter descriptions, the tool's main distribution—the pole issues around sequence—is clearly explained, though optional parameters like meditationDuration aren't explicitly tied into the workflow.

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?

The input schema already gives 100% coverage for all 8 parameters. The description doesn't repeat the schema but genuinely enriches it by grouping the tag enum into process, meta-cognitive, non-dual, skillful-means, and meditation categories, and specifies that begin is the mandatory first tag. That adds meaning beyond the schema's generic 'Current processing technique' description.

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 opens with 'Contemplative reasoning tool' and specifies concrete applications: complex problems needing multi-perspective understanding, contradictions requiring integration, and questions holding their own wisdom. It clearly identifies a reasoning resource. However, it does not differentiate itself from the sibling tool lotuswisdom_summary, which prevents a 5.

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 explicit guidance on how to drive the tool: always start with tag='begin', continue through structured contemplation tags, and avoid producing final wisdom until status='WISDOM_READY'. It gives clear context for when to use it (complex, multi-perspective, contradiction-heavy problems), but it never states exclusions or when to use lotuswisdom_summary instead, so it falls short of a 5.

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