mcp_add

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

Annotations provide only readOnlyHint=false, so the description carries most of the burden, and it does add one genuinely useful behavior: registration is dynamic and tools become available immediately under a protocol.name.operation prefix. It omits durability (persisted or session-only), the allowWrite gating model, and what happens for unsupported protocols or configs, which matters for an additive management operation.

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 short sentences, front-loaded with the action and then the observable consequence. Nothing is padding; the naming pattern is the one detail an agent could not get from the schema.

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?

The enormous config schema is fully self-documenting and there is no output schema, so return values need no explanation. Still, for a state-changing registration tool with minimal annotations, the description leaves out whether registrations survive restarts, default permission posture for writes, and failure modes for unknown protocols.

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% and the config property already enumerates every protocol's required shape in exhaustive detail, so the schema does the heavy lifting. The description adds no parameter-level meaning beyond that baseline.

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: 'Dynamically register a protocol endpoint', and explains the observable effect (namespaced tools appear as protocol.name.operation). It does not, however, distinguish itself from close siblings like mcp_add_from_discovery or capability_register, which an agent must choose between.

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?

There is no when-to-use guidance and no exclusion of alternatives, despite the sibling list containing mcp_add_from_discovery (adds from discovery), mcp_plan_bridge, and capability_register, all plausible confusions. The agent must infer the selection rule from the names alone.

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