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

Annotations already cover readOnly, idempotent and non-destructive, so repeating 'Read-only' earns little. What the description does add beyond structured fields is the token semantics (site token valid pre-claim) and the billing trait 'Does not charge', which no annotation expresses. Return payload shape and any path-count limits remain undisclosed.

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?

Short and largely front-loaded, leading with the auth requirement and the resource, then the address format, then the token rules. The trailing 'Read-only. Does not charge.' is two fragments that partially duplicate annotations, modest waste but defensible for a billing-sensitive operation.

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 one-parameter, no-output-schema read tool whose annotations already declare the safety profile, the description covers the remaining unknowns an agent needs: auth path, the pre-claim token exception, and the absence of cost. Nothing blocking a correct invocation 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?

Schema description coverage is 100% and there is a single parameter, so the schema already defines 'site' fully. The description merely restates the schema's own example ('myproject.dropthehassle.app') verbatim, adding no format, constraint or validation detail beyond it. Baseline 3 applies.

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 — 'Lists file paths on a site' — which an agent can separate from get_site_file (single file) and edit_site_file (mutation). However, it never names those siblings explicitly, so the differentiation is inferable rather than stated.

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?

Gives real preconditions: an account token is needed, a site token works including before the site is claimed, and without a token the site must be claimed first. That is clear context for when the call will succeed, though it never contrasts with the sibling read tools (get_site_file) that might also return file content.

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