extract_note_facts

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

Annotations already convey read-only, idempotent, and non-destructive hints. The description goes beyond these by revealing that content in ambiguity_flags should remain 'undecided' in the minutes, and by noting that truncated_categories indicates categories that were cut due to limits. This provides actionable behavioral context that helps the agent use the output correctly.

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 structured with a clear opening purpose, a rationale, a list of returns, then Args/Returns/Examples sections. It is informative but not overly verbose, though some repetition (e.g., restating default value) could be trimmed. Front-loading the purpose and usage examples makes it easy to scan.

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 with multiple output categories and an existing output schema, the description provides sufficient context: what it returns, how to interpret ambiguity_flags, and when to use it. The examples cover both positive and negative usage cases, making it complete for an agent to call the tool correctly in a 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?

Both parameters are fully described in the schema (100% coverage), so the description adds no substantive new semantic information. It restates the default value of max_items_per_category and its purpose ('context protection') but this closely mirrors the schema. Baseline 3 is appropriate because the schema does the heavy lifting.

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 extracts 'quotable facts' with line numbers from the original text before drafting, listing specific categories (attendees, speech lines, date expressions, decision candidates, action item candidates, ambiguity flags). It distinguishes itself from sibling check_minutes_grounding by explicitly stating it is not for verifying completed drafts, making its purpose and differentiation unambiguous.

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 usage scenarios: 'use right before draft writing' and 'when evidence check gives a warning', and a clear non-use case: 'do not use when verifying a completed draft, use check_minutes_grounding instead'. This gives an agent precise conditions for when to invoke this tool versus alternatives.

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