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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's added value is the "does NOT replace stored turn/message history" guarantee, which tells the agent exactly what this write will not destroy. It doesn't state whether unmentioned fields are preserved or whether partial failure is possible, keeping it below a 5.

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?

Two short sentences plus a redirect, with the core action front-loaded and zero filler. Every clause carries information the agent needs (what it patches, what it doesn't, where to go instead).

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?

The safety profile is covered by annotations and no output schema is required to be explained, so the main gaps are the undefined notion of a "light conversation document" and the undocumented field set of the nested object. An agent knows the tool's boundaries but not precisely what a valid patch payload looks like.

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 three parameters are documented structurally and the baseline is 3. The description adds nothing about which conversation fields the nested `conversation` object accepts — a real gap since that object has no declared properties — but per the coverage rule the schema is doing 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?

"Patch fields on the light conversation document" states a specific verb (patch) and resource (conversation document), and the second sentence explicitly contrasts it with update_conversation_messages. An agent can distinguish this from the transcript-editing sibling without inspecting either schema.

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?

It names the alternative (update_conversation_messages) and the condition that selects it (replacing transcript turns), which is the most likely confusion point. It stops short of covering other related siblings such as update_conversation_note or of stating prerequisites like the agent/conversation needing to exist.

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