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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description then adds real behavioral context beyond them: signature is null when no signing key exists, the public key discovery URL, and that no token is required. It doesn't address rate limits or failure modes, but adds solid value over structured fields.

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-loads the return payload, then the inputs, then the auth/key-discovery detail in one compact, waste-free block. Every sentence (payload fields, nullable signature, key URL, no token) carries information the caller needs.

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 no output schema, the description carries the full burden of describing the return value, and it does so thoroughly (field list plus signature nullability). Combined with the auth note and key-discovery URL, an agent has everything needed to call and interpret the result.

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 50%: the 'version' parameter is already documented in the schema as 'Omit for the live version', which the description largely repeats, while 'slug' remains undefined in both places. At this coverage level the description only marginally compensates, so a baseline 3 is appropriate.

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 resource (canonical manifest for a site version) and enumerates the payload contents (paths, sha256, sizes, version, slug, created_at, Ed25519 signature). This is clearly distinguishable from siblings like get_site and list_versions 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?

Explains the conditional behavior of the optional version input ('When version is omitted, the result is the live site') and states that no token is required, giving the agent enough context to invoke it. It stops short of naming alternative tools (e.g., list_versions) or when-not-to-use guidance, so no explicit exclusions.

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