extract_note_facts

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

Annotations already declare this is a read-only, idempotent, non-destructive operation, so the safety profile is covered. Beyond that, the description adds valuable behavioral context: it discloses exactly what categories it returns (attendees, lines, dates, decision/action candidates) and the key semantics of ambiguity_flags — that flagged content should remain 'undetermined' in the minutes. The truncated_categories behavior is also surfaced. No contradiction with 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 front-loaded with the core purpose and rationale, then uses clear Args/Returns/Examples sections. It is slightly verbose — the anti-hallucination philosophy paragraph is contextually useful but could be tightened. Overall well-structured with no wasted 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?

Given the output schema (NoteFactsResponse) documents the return structure, the description appropriately focuses elsewhere: how to use it, when not to, and the ambiguity_flags contract for post-processing. The truncated_categories edge case is disclosed. The only mild gap is that it doesn't explicitly state the line-number anchoring behavior is by source line, though that's implied. Near-complete for an agent to call correctly.

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 description coverage is 100%, so the schema already documents both parameters, including max_items_per_category's 'context protection' purpose and its default/range. The description's Args section mostly restates this information without adding new meaning, so the schema carries the load. Baseline 3 is appropriate.

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 states a specific verb+resource+objective: extracting 'citable facts' from the source text along with line numbers, before draft writing. It clearly distinguishes itself from check_minutes_grounding, which validates completed drafts. The inclusion of the anti-hallucination anchoring rationale clarifies both what it does and why it exists.

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 Examples section is exemplary: it names two explicit 'use' scenarios (before drafting, when grounding fails) and one explicit 'do not use' scenario with a named alternative (check_minutes_grounding for validating finished drafts). The agent gets direct routing instructions rather than having to infer fit.

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