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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new behavioral detail: edits to the allow-list apply live while toggling enabled only takes effect on the next deploy. That timing distinction is critical and unobtainable from structured fields. It stops short of warning that flipping enabled=true can immediately cut off existing egress traffic.

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?

Three dense sentences with the core definition front-loaded, then the enable semantics, then the application timing. No filler and no repetition of the title.

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 three-parameter mutation with no output schema, the description covers the allow-list format, the deny-by-default model, and propagation timing. Remaining gaps are minor: it does not state what is returned after the call or how an invalid or empty allow-list with enabled=true is handled.

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 33% (only project_id is documented), so the description must compensate. It does: enabled is explained as default-deny toggling, and allowlist entries are described as exact hosts or *.domain wildcards, which is meaning the schema's plain array of strings does not convey.

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 ('Set a project's egress allow-list') and immediately defines the semantics of the allow-list. An agent can distinguish this write operation from the read-only get_egress_policy sibling without opening any 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?

Usage is implied by the semantics of enabled (default-deny when true), but the description never says when to use this versus get_egress_policy to inspect current state, nor does it state prerequisites such as required permissions. The reader can infer the purpose but not the routing decision.

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