update_mcp_server_capabilities

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

Adds real behavioral context beyond the annotations: changes apply immediately and take precedence over integration-level settings, which is the key precedence semantic an agent needs. Annotations already cover safety (destructiveHint=false, openWorldHint=true, idempotentHint=false), so this is additive rather than redundant. It does not explain what happens to capabilities omitted from the array or to unknown capability names.

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 tight sentences: the action leads, the behavioral consequence follows, and the prerequisite tool is named last. Zero filler and nothing that could be cut without losing information.

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 full schema coverage, rich annotations, and an output schema, the description covers action, precedence, and the inspection prerequisite. Remaining gap is the partial-update semantics for capabilities not listed in the array, which matters for a non-idempotent mutation tool.

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% for both parameters, including nested name/type/enabled fields and a required minItems=1 array, so the schema does the heavy lifting. The description adds no extra semantics such as whether unspecified capabilities are left untouched or how the update is applied, so baseline 3 applies.

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 pair (enable/disable) and resource (capabilities on an MCP server). It also implicitly distinguishes itself from the adjacent update_mcp_integration_capabilities by noting that these settings override integration-level ones, so an agent can pick the right scope without opening 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?

Explicitly routes the agent to list_mcp_server_capabilities as a required first step to inspect the current surface, and the override clause tells the agent when this per-server tool is preferable to integration-level configuration. It stops short of stating when not to use it (e.g., bulk cross-server changes).

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