content_gaps

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

With zero annotations, the description carries the full behavioral burden and excels. The POSITION section discloses that position is an impression-weighted average, explicitly warns it is not a rank-tracker rank, notes sparse data beyond page one, and instructs treating absolute positions as directional while preferring deltas. It also imposes analysis rules (report exact numbers only, no speculation, admit insufficient data) and presentation rules (dashboard-style artifacts with cards, colour-coding, charts, tabs) that an agent must follow.

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 description is long but every section earns its place and it is front-loaded with the purpose. The clear section markers (IMPORTANT, PRESENTATION, POSITION) make distinct concerns scannable. The PRESENTATION section is the most verbose, enumerating many visualization details, yet it is actionable and specific rather than filler.

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 3-optional-param analytics tool with no annotations and no output schema, the description compensates well: it explains what is returned (queries with impressions beyond position 20), supplies statistical caveats, and sets analysis and presentation expectations. The only notable gap is that it never enumerates the exact return fields or any limits/pagination behavior, which matters because 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 the baseline is 3. The description adds substantial meaning beyond the schema for min_position: it explains that the position filter is an impression-weighted blended average, warns about sparse data at deep positions, and advises preferring period-over-period deltas — genuinely useful for interpreting a threshold parameter correctly. The days and min_impressions parameters receive no extra elaboration, but the schema descriptions already suffice.

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?

Opens with a specific action and resource: 'Find topics you should create content for', then defines the precise selection rule: 'queries where you get impressions but rank beyond position 20'. This distinguishes it from siblings like content_decay (declining existing content), quick_wins (easy ranking gains), and ctr_opportunities (click-through fixes), since it targets missing content for queries that already have search demand.

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?

Provides clear context for when the tool applies: when there is search demand but no real content targeting it. However, it never names sibling alternatives or states when NOT to use the tool, leaving the agent to infer the selection boundary against near-neighbors like content_recommendations based on the criteria alone.

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