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

Annotations already declare readOnly=false and destructive=false; the description adds the meaningful behavioral fact that this is a partial update where omitted fields are preserved. It says nothing about permissions, revision conflicts, or side effects, and the useful note that saving config does not place a call lives only in the schema, not the description.

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, front-loaded with the action and followed by the one non-obvious rule. No filler.

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?

Adequate for a mutation tool with rich schema coverage and annotations, but thin on context an agent would want: no mention of the related set_assistant_tools/set_assistant_knowledge siblings that own other assistant configuration, and no note on permissions or what the update returns.

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% and all three parameters (id, data, if_revision) are documented in-schema, including the If-Match/409 reload behavior. The description adds only the general patch semantic, which is baseline-appropriate given 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?

States a specific verb and resource ("Update selected assistant fields") and immediately clarifies patch semantics with "Omitted fields retain their values." It is clearly distinct from create_assistant/delete_assistant, though it never names those siblings explicitly.

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 partial-update statement implies this is the tool for modifying an existing assistant rather than replacing it, which is useful implicit guidance. However, there is no explicit when-to-use framing, no mention of prerequisites (the assistant must exist), and no routing to related siblings like set_assistant_tools or set_assistant_knowledge.

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