Run a local rank grid

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

With annotations only declaring the generic write/open-world/non-idempotent profile, the description carries real behavioral weight: one credit per point with worked cost examples, sea points skipped and uncharged, refund on failure, free mock grids for gga_test_ keys, and the wait_seconds-then-return-id timing contract. This is exactly the context an agent needs before spending credits.

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 purpose leads, then cost, then timing/refund, then test-key behavior. Dense but every clause is actionable; the enumerated cost examples (9/49/81, medium circle 29) are verbose yet genuinely useful for predicting spend.

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 10-parameter tool with no output schema and no field descriptions, the description covers the hardest parts: billing, partial-failure refunds, mock mode, and what is returned when the run outlives wait_seconds. The remaining gap is location resolution (place_id vs keyword vs radius_km), which an agent cannot resolve from either schema or description.

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 0% across 10 parameters, so the description must compensate. It clarifies size (3/5/7/9), shape and density vocabularies, and wait_seconds semantics, but leaves keyword, query, place_id, radius_km, country and language entirely unexplained, including how the grid center is anchored.

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?

The description gives a specific verb and resource: measuring Google Business Profile rank on Google Maps across every point of a grid around a location. It is far more concrete than a restated title, but it never names the closest siblings (estimate_grid for cost-only, run_grids for batch), so an agent must infer the distinction.

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?

Usage is implied (this is the tool that actually consumes credits and produces a grid id), and the credit/test-key/refund notes give some decision context. However, there is no explicit 'use this instead of estimate_grid when...' routing, and no stated prerequisites for the required keyword.

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