add_shared_negative_keywords

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

Annotations establish readOnly=false, openWorld=true, destructive=false; the description builds on them by specifying the autonomy trigger — 'measured search-term evidence... clears the policy threshold with no conversions' — the cross-campaign aggregation scope, and the hard prerequisite that the list 'must already exist and be attached to at least one campaign.' It does not address partial-failure behavior or the dry_run escape hatch, so it stops short of a 5.

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?

Purpose is front-loaded in sentence one, behavior in sentence two, prerequisites/workflow in sentence three — a logical order where each sentence earns its place. The middle sentence is dense but carries unique information (autonomy rule, aggregation, sibling comparison); it could be tightened but is not padded.

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?

Covers purpose, scope, autonomy criteria, prerequisite, creation workflow via mutate, and sibling routing; output schema exists so return values are covered. The notable gaps are match_type semantics and the dry_run parameter at 0% schema coverage — for an autonomous write tool those are meaningful omissions, so a 4 rather than a 5.

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 has 0% description coverage, so the description must compensate. It adds real meaning for shared_set_id (must be an existing, attached list) and terms (each needs measured search-term evidence), but leaves match_type (default PHRASE), dry_run, run_id, and rationale undocumented in both schema and description. Partial compensation only.

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 negative keywords to a SHARED list' and immediately distinguishes the scope from the sibling — 'applies account-wide rather than to a single campaign.' It explicitly names add_negative_keywords as the single-campaign counterpart, so an agent can tell them apart without opening schemas.

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 explicit when-to-use ('junk that applies account-wide'), names the alternative (add_negative_keywords) with the same evidence bar, and spells out prerequisites and ordering: 'create and attach it via mutate first (shared_set create, then campaign_shared_set create)' plus a pointer to list_shared_negative_lists for discovery. This is concrete routing guidance, not hand-waving.

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