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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered, but the description adds genuinely useful context beyond them: the Admin / all-sites read-only token requirement, the token-scoping failure mode, result ordering, and cursor paging. It stops short of 5 only because it says nothing about rate limits or error behavior on an unscoped token.

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?

Four short sentences, all front-loaded: purpose and return fields first, then auth constraint and alternative, then paging, then the HTTP path. No sentence is redundant.

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 compensates by enumerating the returned fields, and it covers auth prerequisites, the token-scoping exception, the sibling alternative, and paging. Nothing an agent needs to invoke this 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?

Schema description coverage is 100%, so limit, ending_before and starting_after are already documented in the schema. The description's paging note ('pass next.starting_after') largely restates the schema's own wording for starting_after and adds no new semantics, so the baseline of 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?

Specific verb and resource (list sites the token can read), lists the returned fields (id, name, sharing, timezone, created_at) and the ordering (oldest first). It is clearly distinguished from the singular fathom_get_site sibling referenced in the description.

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 explicit when-not guidance: 'a token scoped to a single site cannot list sites, so use fathom_get_site with that site id instead,' which names the alternative and the condition that selects it. Paging usage is also specified ('pass next.starting_after').

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