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

With no annotations, the description carries the full burden and does reasonably well: it discloses the auth requirement (api_key or X-API-Key header), and crucially warns that supplying tile triggers a different operation (POST /v1/tenant/try) that is 'counted on your tenant' — an important side-effect/quota disclosure. It stops short of describing pagination, error behavior, or what the GET returns structurally.

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 a single sprawling run-on sentence cramming returned fields, auth, and the tile mode-switch together. The most important operational fact (the tile-triggered POST that counts against the tenant) is buried mid-sentence rather than front-loaded, hurting scannability.

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-param, no-output-schema, no-annotation tool, the description covers auth and the tile side-effect but leaves the tile enum semantics and return shape unexplained. It is marginally adequate but has clear gaps for a tool whose parameters carry enum ambiguity.

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%, so the description must compensate. It explains api_key (auth source, including header alternative) and clarifies that range is a time window for traffic (1d|7d|30d|90d), which adds meaning. But it never explains what the eight tile enum values (demand, catalog, pool, rpc, proof, grade, gpu, bridge) actually do, leaving the highest-cardinality parameter under-specified.

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 indicates this returns tenant-level data (id, keys, traffic, credits) and maps to GET /v1/tenant/me, so the resource is identifiable. However, the purpose is buried in a dense enumeration of returned fields ('demands, settles, pools, grades, credits, spend; plus GRID accrued... and GPU credit at the gate') and the dual mode (tile = sandbox action) muddies whether it is a read or an action tool. It never cleanly states what the tool IS in one clause, and it does not distinguish itself from siblings like taifoon_metrics or taifoon_network.

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?

It does provide a conditional usage rule: 'With tile, runs that sandbox action instead (POST /v1/tenant/try), counted on your tenant,' which tells the agent when the tool switches behavior. It also states auth requirements ('Needs your key...'). But there is no guidance on when to prefer this over sibling tools that surface overlapping data (metrics, network, landscape).

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