channels_credentials_patch

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

Annotations already flag readOnly=false, destructive=true, openWorld=true, and the description is consistent with them while adding real context: the deep-merge semantics, the fact the change reaches the platform, and the explicit expectation of user confirmation. That is useful detail beyond the flags, though it stops short of describing reversibility or what gets preserved.

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?

The purpose sentence is tight and front-loaded, which is good. The second sentence is generic boilerplate applicable to almost any destructive tool rather than specific to this operation, and the trailing parenthetical restates transport details that add little selection value.

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 two-parameter destructive mutation with no output schema, the description covers the safety posture (destructive, reaches others, confirm first) and the merge behavior that the annotations alone would not convey. What remains thin is identification of the channel id's format and the effect on unspecified fields, but the core calling requirements are present.

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?

The credentials parameter's merge behavior (objects merge, arrays/scalars replace) is already spelled out in the schema, so the description's 'deep-merge' phrasing repeats rather than extends it. The id parameter is undocumented in both places, and at 50% coverage the description does not compensate for that gap. Baseline 3 is appropriate.

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: 'Deep-merge fields into a channel's stored credentials'. This clearly distinguishes the tool from a plain settings update, and the parenthetical names the underlying endpoint/gRPC method. It does not, however, explicitly contrast against channels_update or channels_create, so an agent must infer the boundary itself.

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 second sentence communicates a requirement before acting: say exactly what will happen and obtain the user's confirmation first, which is genuine procedural guidance for a destructive call. It does not, however, say when to prefer this over channels_update or other credential-adjacent siblings, so usage direction is only implied.

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