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

Annotations already declare readOnly/idempotent/non-destructive; the description adds real value on top: return shape (one-line answer plus confirmed changes, newest first), a default/limit window (90, max 365), and an important honesty caveat that absence of changes is not a safety guarantee. It also discloses a data boundary ('never includes tool description text'), though it says nothing about rate limits or auth.

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?

Information-dense with no wasted clauses, but the rhetorical opener ('ask whether apiwatch saw them change') delays the actual action statement. The operational content — inputs, window, return shape, caveat — is all present and mostly 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 two-parameter read tool with full schema coverage, complete annotations and an output schema, the description covers everything an agent needs: what it reports, how to identify the server, the time window, ordering, and the interpretive caveat about 'no changes'.

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 100% and the description merely restates what the schema already documents: accepted server formats (slug, URL, registry name) and the 90/365 day window. No added syntax, precedence rules, or failure behavior for unresolvable server identifiers.

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?

The description states a concrete resource and scope: tool-level changes (removed, renamed, new required params, rewritten descriptions, changed safety hints) for one named MCP server. That is specific enough for an agent to distinguish it from a broad change search, though it never names a sibling like search_changes or list_watched_mcp_servers to sharpen the boundary.

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?

It gives a clear trigger — 'Before you rely on a public MCP server's tools' — and a prerequisite hint via 'a watched server's slug'. It stops short of explicit exclusions or naming which sibling to use for unwatched servers or cross-server change hunting.

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