add_keywords

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

The description adds real behavioral context beyond annotations (preview semantics, dedup of already-tracked keywords, the confirm_action approval flow). However, 'PREVIEW ONLY' asserts the call does not change state, which conflicts with readOnlyHint=false — the annotation declares a mutating operation while the description declares a non-mutating one.

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 short sentences with the most constraining fact ('PREVIEW ONLY') front-loaded, followed by the dedup rule and the confirm step. The middle sentence is slightly convoluted in wording but every sentence carries load.

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 two-parameter staged tool with no output schema, the description covers the essential: it is a preview, duplicates are not re-added, and confirm_action performs the commit. Missing only edge details (partial-failure behavior, limits beyond the schema's 50) that are minor here.

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% and both parameters are documented in the schema (appId from list_apps, up to 50 keywords). The description adds no additional parameter-level meaning (no casing rules, no duplicate handling syntax), so the schema does the heavy lifting and 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?

States a specific verb + resource ('add keywords to an app's tracked list') and clarifies that already-tracked keywords are deduped. It does not, however, distinguish itself from the closely-named siblings add_exact_keyword or add_negative_keyword, which do similar-looking things, so the agent must still infer the boundary.

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?

'PREVIEW ONLY' plus 'Apply with confirm_action after the user approves' gives explicit workflow guidance: this tool stages, confirm_action commits. It stops short of saying when to use this tool versus add_exact_keyword/add_negative_keyword, so the sibling boundary is left implicit.

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