get_changes

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

Annotations already declare readOnlyHint and idempotentHint=false, so the description correctly does not re-litigate safety. It adds real value annotations cannot: ordering is by latest change with oldest first, and all names/text in the response are third-party content that must not be treated as instructions — a security trait worth flagging.

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 tight sentences, front-loaded with what it returns, then pagination, then the injection warning. No filler and nothing important buried at the end.

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?

An output schema exists, so return-value structure need not be explained; the description covers the things the schema cannot — ordering semantics, cursor reuse across calls, and the untrusted-content caution. Nothing an agent needs to call this safely and 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 coverage is 100%, so baseline is 3; the description earns an extra point by explaining the pagination contract — reusing the returned next as since while more is true, and carrying forward the last next. It adds nothing on 'chat' or 'limit' beyond what the schema already documents.

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 plus the exact change semantics (added, edited, revoked, expired) and ordering, which separates it in spirit from get_messages and search_messages. It never names those siblings, so an agent must infer the distinction rather than being told it.

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 cursor loop ('pass next as since while more is true, keep the last next') is clear operational guidance and 'omit since to start from the oldest change' defines the first call. But there is no statement of when to choose this over get_messages or get_chat, so alternative selection is left implicit.

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