site_selection_canvas

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description's main transparency value is adding context beyond those. The description details the flow (find->rank->shortlist->verdict), mentions a paid key unlocks additional features, and implies US-only scope. This adds meaningful behavioral context without contradicting annotations. While not perfect (e.g., no mention of response size limits), it is strong.

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 efficient: one paragraph with every sentence serving a purpose. It starts with the core purpose, then details outputs, gives an example, and ends with exclusions. There is no redundancy or fluff. The front-loading is excellent.

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?

Given the tool's complexity (5 parameters, no output schema), the description covers inputs, outputs (ranked shortlist with key attributes, paid layer adds more), usage boundaries (US markets, paid key requirement), and exclusions. It provides enough context for an agent to understand the tool's role and how to invoke it correctly, despite the absence of an output schema.

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 100% with each parameter having a clear description. The description adds value by providing an example call (capacity_mw=100 region=TX max_months=24) and implying that certain parameters are effectively required (capacity, geography, deadline) even though the schema lists them as optional. This goes beyond the schema's individual descriptions, warranting a score above the baseline of 3.

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 clearly states the tool's purpose: 'Guided end-to-end data-center site selection.' It specifies the verb (guide/run), resource (site selection canvas), and outputs (ranked shortlist with DCPI verdict, etc.). It distinguishes from siblings by explicitly saying when NOT to use it and naming alternatives (analyze_site, get_dchub_recommendation). This meets the criteria for a specific verb+resource and sibling differentiation.

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?

The description provides explicit usage guidance: 'Give a capacity target + geography + deadline and get a ranked shortlist of US markets.' It also gives a concrete example (site_selection_canvas capacity_mw=100 region=TX max_months=24). Crucially, it states when NOT to use it: for a single known parcel (use analyze_site) or open-ended where-should-I-build (use get_dchub_recommendation). This is excellent contextual guidance.

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