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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the mutation/repeatability profile is covered. The description adds a genuine side-effect disclosure those annotations cannot convey: pointing at a new query_id means 'today's list is emailed again', i.e. re-triggering an outbound email. It omits whether partial updates are allowed and what the response looks like.

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?

A single dense sentence that front-loads 'Change an alert's schedule…' and then walks through each modifiable facet, so no sentence is wasted. It is slightly packed with parenthetical enum lists, but nothing is redundant with the title.

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?

With no output schema and full schema description coverage, the description only needs to carry intent and behavioral nuance, which it does: all six parameters' purposes are visible, and the re-email side effect is flagged. It stops short of stating that all fields except alert_id are optional or what is returned after the update.

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 every parameter is already documented in the schema, and the description largely restates the same enum values (after_close, pre_open, weekly; changes or always). The one thing it adds beyond the schema is the consequence of setting query_id. 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?

The description names a specific verb ('Change') and enumerates the exact mutable facets: schedule, notification mode, name, enabled state, and query_id. 'Pause/resume' and 'point it at a refined version' further disambiguate the operation. It does not explicitly name create_alert or delete_alert as siblings to avoid, but the verb alone separates it from them.

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 context is supplied inline: query_id must come from a refine_market_query result 'in the same session', which tells the agent the correct upstream workflow, and 'pause/resume it with enabled' tells it how to suspend an alert versus editing it. There are no explicit when-not-to-use exclusions or direct routing to create_alert/delete_alert, keeping it below a 5.

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