WWDC MCP security manifest

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world posture, so the safety profile is covered. The description adds genuinely non-derivable context: the response includes a manifest hash for drift detection and prompt-injection handling notes, disclosing the tool's security-relevant behavior.

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 tightly packed sentences with zero waste; the return contents are front-loaded and the purpose follows immediately. Every clause earns its place.

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?

Although there is no output schema, the description enumerates the salient returned fields, so an agent knows what to expect. For a zero-required-param, single-enum-param tool, nothing needed to invoke it correctly is missing.

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?

Only one parameter (format) with 100% schema coverage and an enum, so the schema fully documents it. The description adds no additional meaning about format selection, which is the baseline-3 case when the schema does the heavy lifting.

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 (Returns) and enumerates the exact resource contents (tool list, manifest hash, read-only posture, prompt-injection notes, threat-model summary). This is unmistakably distinct from every sibling, which are all content-retrieval or lookup tools.

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 names two use cases: detecting tool-surface drift and reminding agents that retrieved content is untrusted evidence. It gives clear context but names no alternatives or when-not conditions, which is acceptable given no sibling overlaps.

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