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

Annotations already declare readOnly=false, destructive=false and idempotent=true, so the safety profile is covered; the description's real contribution is the merge-vs-replace semantic ('Only the fields given change'), which is not encoded in any annotation and directly affects how an agent should build the call. It still omits how to clear an existing filter (empty array?) and whether invalid values are rejected or silently ignored.

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?

Two short sentences, no filler, with the mutable-field scope front-loaded and the partial-update rule second. Every clause earns its place.

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 13-parameter patch tool with full schema coverage and a complete annotation set, the description plus schema is enough to call it correctly, and no output schema is needed. The gap is unstated behavior for clearing a filter and for what alert_id='main' means in practice, which the schema only partly covers.

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 per-field descriptions, enum values (email_times) and hints pointing at list_filter_options and list_alerts, so the schema does the heavy lifting. The description only groups the fields into categories and adds no syntax or clearing behavior beyond that, so the baseline 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 ('Change') plus resource ('an alert's filters, name, email on/off or times'), and it enumerates the mutable field groups so an agent knows the scope of the edit. It does not name the sibling it differs from (create_alert/delete_alert), but the mutation-of-existing-alert framing is unambiguous.

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?

Usage is implied: this is the tool for modifying an existing alert, and 'Only the fields given change' tells the agent it may send a subset. There is no explicit exclusion or pointer to alternatives such as create_alert for new alerts or list_alerts to find alert_id, so routing is left to inference.

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