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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: an external partner key is required, and a missing key yields an instructional response rather than an error – that is exactly the kind of context an agent cannot infer from annotations. It stops short of describing what the feasibility output contains.

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?

Two sentences, no filler, with the quantity delivered (pre-feasibility report) first and the credential constraint second. Nothing in the text is redundant with the title or annotations.

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?

With no output schema and no parameter descriptions, the definition leaves the core invocation question unresolved: is location supplied as lat/lon, as a free-text address, or either? It also never says what the returned feasibility assessment reports (yield, irradiance, payback), which the agent needs to decide whether to call this at all. Adequate on auth, inadequate on inputs and returns.

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 four parameters, so the description carries the full burden. It explains only api_key (requirement plus fallback); lat, lon and address are left entirely undefined, so the agent must guess whether address is an alternative to coordinates or an additional filter, and with zero required parameters it cannot tell which combination is valid.

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 names a specific resource and output type – a solar pre-feasibility assessment for a factory roof, sourced from PVGIS plus satellite data – so an agent knows what it produces. It does not differentiate from siblings, but the sibling set (list_ventures, network_stats, say_hello, skill_rank) has no topical overlap, so the ambiguity risk is low.

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 prerequisite ('Requires a SolarAnalytics partner API key') and the fallback ('Without a key, returns how to get one') give real call-context, including that it is safe to invoke without credentials. However there is no explicit when-to-use versus alternative framing and no statement of which location input form to pick.

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