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

Annotations only declare the coarse profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false); the description adds the substance: billing on generation, gateway misconfiguration rejected before any request and unbilled, stops on first failure/disabled flag/unknown usage/lost access, eligibility rechecked on executeCursor, and a 50-row page scan meaning hasMore can be true with zero candidates.

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?

Dense but front-loaded: the find-and-generate purpose and the dryRun default come first, with operational caveats packed into the back half. Nearly every clause carries information, though the run-on 'Stops on...' sentence is hard to parse and could be split for readability.

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?

An output schema exists so return values need no explanation. For a non-idempotent, billed, cursor-paginated backfill with a preview mode, the description covers modes, billing, prerequisites, failure semantics, pagination caveats and cursor reuse — nothing material is missing.

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 coverage is 100%, so the schema already documents days, limit, cursor, dryRun and channel, setting the baseline at 3. The description adds real semantics on top: limit default/ceiling and that a time budget can yield fewer, and the non-obvious cursor rule that it only continues the mode that produced it.

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?

States a precise verb+resource pair (find and generate conversation summaries) with a sharply bounded target: conversations with a missing or malformed cached summary, explicitly excluding legacy valid caches. This scoping alone distinguishes it from get_conversation_summary and refresh_conversation_summary without needing to name them.

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?

Gives clear when-to-use guidance: default dryRun=true previews with no model call, billing or writes; dryRun=false generates, is billed to company credits, and requires company AI summaries enabled. It also explains the cursor workflow (executeCursor from a preview, nextCursor only continues its originating mode). It never names refresh_conversation_summary as the alternative for a single conversation, which is the one gap.

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