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

Annotations already establish readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful behavior beyond that: default ordering ('oldest first'), the pagination cursor mechanism, and the underlying REST path GET /sites/{site_id}/milestones. It stops short of return-field or rate-limit detail, but the annotations carry the safety profile.

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 compact sentences: purpose/definition first, then paging, then the endpoint. No filler, no redundancy, and the most decision-relevant information is front-loaded.

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 paged read-only list tool with no output schema, the description covers ordering, cursor-based paging, and the endpoint — enough to call it correctly. The only gap is the shape of returned milestone objects, which an agent could recover via the sibling fathom_get_milestone.

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%, with limit, site_id, ending_before and starting_after all documented in the schema itself. The description repeats the paging cursor ('next.starting_after') and the site_id path segment, adding no semantics the schema lacks. Baseline 3 is appropriate 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 (list) and resource (a site's milestones), then defines the domain term inline as 'dated annotations on reports, such as a redesign launch or a campaign start'. That definition plus the required site_id and ordering ('oldest first') clearly distinguishes it from the singular fathom_get_milestone and the unrelated fathom_list_events/fathom_list_sites siblings.

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?

The description implies the listing use case and gives concrete paging guidance ('Paged: pass next.starting_after'), which is actionable. However, it never states when to use this instead of fathom_get_milestone for a single record, nor any preconditions such as needing a valid site id from fathom_list_sites beyond what the schema already says.

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