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

No annotations are provided, so the description carries the full burden and does so richly: read-only with no side effects beyond charge, cache keyed by pose + scene date, reserve-then-settle charging, 4xx releases the reservation, and idempotency semantics ('a retry here is always a new charge'). It also discloses the auth requirement ('AGENT KEYS ONLY, a browser session is refused BEFORE any charge'). This is far beyond what structured fields supply.

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?

Front-loads the core concept before parameters and billing, which is the right order. It is long and dense with heavy parentheticals and ALL-CAPS emphasis, and a few clauses are redundant (the 'never a fabricated image, never a scene borrowed' point is restated), but given zero schema/annotation help most sentences earn their place.

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?

Despite an output schema existing (so return values needn't be explained), the description covers the frame fields, the available:false behavior, and the full billing/verification workflow. Combined with no annotations and 0% schema coverage, this is complete enough for an agent to call and interpret results correctly.

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?

With 0% schema description coverage across 8 params, the description fully compensates: t0 format (YYYY-MM-DD, on/after 2015-06-23), t1 default today, max_frames range 1-12 default 6 and its windowing semantics, max_cloud 0-100 default 20, and the lat/lng OR entity_type+id pose rule. Ranges, defaults, and formats are all supplied.

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 ('ordered stack of dated Sentinel-2 archive stills of ONE site across a date range') and immediately scopes it against the sibling look_at ('the same pose rule as look_at'). An agent can distinguish it from look_at/look_from without opening either schema, and it explicitly notes what it does NOT do ('does NOT say what changed between frames').

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 clear context: the pose rule, date-range bound, and a mandatory charging workflow ('Quote first: billing_quote("/api/v1/look.through")'). It references look_at's pose and cache, implying the sibling relationship, but never explicitly states when to choose this over look_at for a single still. No explicit exclusions beyond the 'does not say what changed' note.

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