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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered. The description earns credit by adding genuinely new behavioural facts: an authorization role requirement, optimistic concurrency via expectedRevision with stale-revision rejection, and an explicit statement that published offers are untouched. It omits whether omitted nested fields in brand/support are cleared, which matters for a destructive replace.

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?

Three tight sentences, front-loaded with the action and scope, then the preconditions, then the explicit non-effect. No filler or restatement of the title.

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 destructive five-parameter mutation with nested objects, the definition covers authorization, concurrency control and scope exclusion, and an output schema exists so return values need no explanation. The remaining gap is replace-vs-merge behaviour for the nested brand and support objects.

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 60%: partnerId, commercialMode and expectedRevision carry their own descriptions, while brand and support are undocumented at the field level. The description contributes the replace semantics of expectedRevision ("the current profile revision", stale rejected) and the word "Replaces", which implies omitted brand/support members are reset rather than merged, but it never spells that out.

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?

"Replaces the agency brand, support details and requested commercial mode" gives a specific verb plus the exact resource fields touched, and "It does not change any published offer" bounds the blast radius. It stops short of naming which neighbouring agency_profile_* tools handle membership/invite concerns, so an agent must infer that boundary from names alone.

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?

Prerequisites are stated clearly (owner or admin role required, current profile revision required, stale revisions rejected), which tells the agent when the call can succeed. However, there is no guidance on when to choose this over alternatives, nor any explicit "do not use for X" routing beyond the offer exclusion.

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