normalize_idea

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

While annotations indicate non-destructive mutation (readOnly=false, destructive=false) and external interaction (openWorld=true), the description adds valuable behavioral context: it discloses the judgment/verdict mechanism (READY/ALMOST READY/NOT READY), signal analysis outputs, and the guarantee that output 'ALWAYS ends with a commit decision' with specific external destinations (GitHub, Jira, Linear).

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?

Though lengthy, the description is well-structured with clear functional sections (purpose, usage triggers, proactive guidance, output specification). Minor inefficiency exists with poetic/marketing phrases ('This is the moment where thinking stops', 'IdeaLift'), but overall every section serves the agent's understanding.

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?

Despite lacking a formal output schema, the description comprehensively details the return structure through explicit enumeration: Readiness Verdict, Signal Analysis, Structured spec, and Commit options. This adequately compensates for the missing output schema in a complex multi-step tool.

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?

With 50% schema description coverage, the description partially compensates by contextualizing the types of input (meeting notes, Slack threads, feature requests) that map to the 'text' parameter. However, it fails to mention the 'context' parameter or its 'source' enum entirely, leaving that parameter undocumented beyond the schema.

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 specific action ('Transform raw ideas into execution-ready work items') and distinguishes this from sibling tools like create_idea or update_idea by positioning it as a 'COMMIT LAYER' that judges readiness and bridges thinking to execution.

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?

Contains an explicit 'USE this tool when' section with specific intent signals (e.g., 'We should...', 'Feature request:', 'normalize', 'make this backlog-ready') and instructs the agent to 'PROACTIVELY offer' usage when these signals are detected, providing clear guidance on when versus alternatives.

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