Get Change Alerts

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

Annotations say readOnlyHint=false and idempotentHint=false, but the description supplies the reason: the default call marks alerts read, which is a state-mutating side effect an agent must know about. It also discloses ordering (oldest first) and cost ('Free'), both beyond the annotations. It does not say whether the read-marking is reversible or what happens with an empty result, keeping it short of a 5.

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 dense sentences, front-loaded with scope and ordering, then the mutation behavior, then cost. 'Free.' earns its place as a one-word pricing fact, and nothing is filler.

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?

Output schema exists, so return shape need not be explained, yet the description still summarizes alert fields usefully. The one real behavioral risk (marks read by default) is disclosed. Minor gaps: irreversibility of the read-marking and behavior on an empty inbox.

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 50%, with limit and unreadOnly undocumented in the schema. The description compensates by explaining the default unread-only behavior and the mark-as-read side effect, which gives meaning to unreadOnly and markRead beyond their names. It adds nothing about limit or pagination, so a sample of the semantics is still missing.

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 resource (alerts), a scope restriction ('this caller's watched domains'), and an ordering ('oldest first'). The addition of what each alert contains (domain, change type, old/new values, severity) makes the purpose unambiguous and separates it from siblings like list_watches or domain_history.

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?

Implied usage is inferable from 'by default returns unread alerts and marks them read', but there is no explicit when-to-use versus alternatives such as domain_history or watch_domain. No guidance on when to set markRead=false or unreadOnly=false, or on choosing between them.

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