mcp_blacklist_add

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

With readOnlyHint=false the annotation already signals a write, and the description adds real behavioral context: it names exactly what gets blocked (mcp_add, discovery register, invoke) and notes that blacklisting 'still applies in Full mode', which is non-obvious policy detail. It omits reversibility and auth requirements, but disclosure is well beyond annotation coverage.

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?

Front-loaded with the verb and resource, then the three modes follow in compact clauses. It is dense but nearly every clause carries distinct meaning; minor redundancy in restating that each mode both hides and blocks.

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 an 8-parameter mutation tool with no output schema, the description covers the essential semantics (mode selection and pattern syntax) needed to invoke it correctly. It stops short of covering the reason field or any return/confirmation behavior, but annotations already carry the safety profile.

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 only 38%, so the description must compensate, and it does: it maps host+port/url to target, adapterId (protocol:name) to capability, and pattern to tool, plus it documents glob syntax (* = one segment, ** = any) not present in the schema. Only the reason parameter is left unexplained, keeping it just shy of full coverage.

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 (Add) and resource (blacklist entry), then enumerates the three operational modes (target, capability, tool) with their distinct targets. An agent can distinguish this from siblings like mcp_blacklist_remove or mcp_remove purely from the description.

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 description effectively routes within the tool by explaining what each kind does (kind=target for protocol+host/port or url, kind=capability for adapterId, kind=tool for glob patterns), which tells the agent when to pick each mode. It lacks explicit guidance on when to use this tool versus alternatives like mcp_remove, so no exclusions are stated.

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