Change filter settings

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

Annotations already flag destructiveHint=true, and the description adds real behavior on top: the default dry-run guard, the confirmLive precondition during streaming/recording, the overlay merge-vs-replace semantics, and the fact that a before/after diff is returned. That is well beyond what the structured fields convey.

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 with the core action and the overlay default front-loaded, then the guard conditions. No filler, though the parenthetical '(including Source Record)' is a slightly awkward insertion.

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 destructive mutation with no output schema, the description covers the safety model (dry-run default, live confirmation) and mentions the diff result. The main gap is the settings object contents, which neither the description nor the schema constrains.

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 67%, with dry_run, overlay, and confirmLive already documented in the schema; the description largely restates those defaults rather than adding new semantics. It adds nothing for sourceName, filterName, or the shape of the settings object, so it does not compensate for the uncovered parameters.

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 ('Changes settings of a filter') and notes the Source Record case, which distinguishes it from set_filter_enabled and set_filter_index in the sibling list. It stops short of naming an alternative tool outright, so it is clear but not fully sibling-differentiated.

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?

Gives concrete usage conditions: overlay defaults to merge-only, dry_run defaults on, and confirmLive=true is required while streaming or recording with the instruction to ask the person first. This tells the agent when the call is safe versus when it needs a live confirmation, though it never routes to a sibling tool.

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