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

Annotations already cover the safety profile (destructiveHint=true, idempotentHint=false). The description adds valuable context beyond them: omitted fields are preserved, and when an evaluation suite exists, voice or tool changes rerun it first with nothing saved on failure — an unusual gating behavior an agent could not infer from structured fields.

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 tightly packed sentences with zero waste. The scope of changeable fields is front-loaded, followed by the key behavioral caveats (partial update, eval rerun, model exclusion).

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?

With no output schema to explain return values, the description still covers everything an agent needs: what changes, partial-update behavior, eval gating, and the model exclusion. Annotations handle the destructive/idempotency profile, so 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 description coverage is 83% (high), so the schema does most of the work and baseline 3 applies. The description adds meaning on top by clarifying that all fields are optional and unset fields retain prior values, which sharpens the semantics of the optional parameters.

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 (change/update) and resource (AI agent), then enumerates exactly what can be changed: name, tone, instructions, handoff threshold, low-confidence behavior, and tools. This makes it immediately distinguishable from siblings like get_agent (read) and update_ai_settings.

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 clearly states partial-update semantics ("Anything left out stays") and gives an explicit exclusion ("This action does not change the model"), which implicitly routes model changes to update_ai_settings. It lacks an explicit named alternative, so it stops short of full when/when-not routing.

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