Don't target a phrase

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

Goes well past the annotations by disclosing the downstream effect of listing a phrase: it is omitted from every AI step (suggestions, listing options, localization, screenshot headings) and from drafts, and hidden from tracked keywords. It also tells the agent where to verify state (get_project_board under dontTarget), which the idempotentHint/non-destructive annotations cannot 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?

The add/remove behavior is front-loaded in the first clause, followed by the consequence and then the discovery pointer. Two sentences, no filler, and the parenthetical example earns its place by clarifying intended use.

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 4-parameter mutation with no output schema, the description covers the operation, its side effects, and where the resulting list is visible. The only missing piece is what the call returns on success (the updated list vs. an acknowledgement), a minor gap given no output schema exists.

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 phrase, remove and projectId are already documented. The description only adds a rationale for note ('e.g. a rival's brand') and restates remove:true, so it is marginally useful rather than compensating for any gap — 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?

Names a specific verb and resource ('Put a phrase on the project's "don't target" list') and covers the inverse operation in the same breath ('take it off with remove:true'). It also points to the sibling that surfaces the list (get_project_board), so an agent can distinguish this from add_keywords/remove_keywords without opening a schema.

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 context for calling it is clear: to exclude a phrase (e.g. a rival's brand) from all AI output, or to un-exclude with remove:true. It stops short of explicit exclusions — it never says whether this is the right tool vs. edit_keyword for tracked keywords, though the 'tracked keyword with that label is hidden' clause implies the relationship.

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