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

Annotations only declare non-destructive mutation; the description adds genuinely new context such as the required 'act' scope, that there is no spend or posting, idempotency via a stable run_key, and that it never authorises drafting. Some of this ('preserves evidence holds', 'never authorises drafting') is cryptically worded, but the added behavioral signal is substantial.

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 purpose is front-loaded in the first sentence, but the remainder is a dense, run-on block of qualifications that mixes parameter rules, scope requirements, and cross-tool routing. Most sentences carry information, yet the phrasing ('never authorises drafting', 'preserves evidence holds') is compressed to the point of being hard to parse.

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?

For a 14-parameter tool with 0% schema coverage, nested objects, and no output schema, the description should cover more. It addresses the research and draft paths reasonably but omits the idea-path basics (why, text, title, channel) and any sense of what the call returns or how run_key dedup behaves on replay.

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 0% across 14 parameters, so the description must carry the load. It names several parameters (operation, research with method/limitations/sources, expected_updated_at, action_kind, idea_id/source_idea, source_url, adopt_legacy), but leaves why, text, title, channel and claim_ids entirely unexplained, so compensation is partial.

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 opening sentence gives a specific verb (file) and three concrete payloads (growth idea, original X draft, research outcome), so an agent can tell what the tool records. It doesn't explicitly differentiate itself from siblings like record_insight or record_claim, which handle adjacent content types, so sibling disambiguation is only partial.

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 gives real routing guidance: use adopt_legacy only to classify an exact saved replay, read get_move and use existing move verbs for completion, and new drafts need action_kind social_post plus one idea_id or source_idea. It stops short of a clean when-to-use / when-not-to-use statement for the three operations themselves.

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