reflect

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

Annotations set readOnlyHint=false, implying the tool may have side effects, but the description only describes building and returning data with no mention of side effects. This is a clear contradiction. Additionally, no behavioral traits are disclosed beyond 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 a single paragraph that front-loads the main purpose but includes version numbers and future plans that are not directly actionable for the agent. It could be more concise by removing the version-specific details.

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 complexity of generating an LLM abstraction, the description omits key details such as what constitutes 'recent decisions and sessions', how the context is built, and any prerequisites or state dependencies. The return structure is mentioned but lacks explanation of fields.

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 has two parameters (dry_run, period_days) with defaults and no descriptions. The description does not explain their meaning or usage at all, providing no value beyond the schema's parameter names.

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's purpose: building source context and a rendered prompt for an LLM abstraction over recent decisions and sessions. It uses a specific verb ('build') and resource ('context+prompt'), and distinguishes itself from sibling tools by focusing on reflection generation.

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 guidance on when to use this tool versus the CLI alternative `codevira reflect --from-file`, noting that MCP sampling integration is not yet available. However, it does not explicitly state when not to use the tool or compare with other sibling tools for similar tasks.

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