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

Annotations already establish read-only, idempotent, non-destructive, closed-world semantics, so the bar is lower, and the description still adds real behavioral context: Bearer-token authentication with a personal key, a free tier that returns rounded example values versus a Premium tier with low/high figures, and a metered cost of one run per answer. That billing and entitlement disclosure is exactly the kind of trait annotations cannot express. It does not describe caching, latency, or per-key rate ceilings, which keeps it from a 5.

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 dense sentences: the first front-loads what the tool returns, the second covers auth, entitlement tiers, cost accounting, and valid inputs. Every clause carries information, but the first sentence is a long comma-separated list that is heavier than it needs to be; a short lead sentence plus the field list would scan faster.

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, the description bears the burden of describing the response, and it does so partially: it names the figures returned and explains that free keys yield rounded example values while Premium keys return figures with low and high bounds. Auth requirements and the set of valid markets are also covered. The one residual gap is the precise shape of the response (nesting, units per field, how low/high are represented), which is left implicit.

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?

There is a single parameter at 100% schema description coverage, so the baseline would be 3. The description earns above baseline by enumerating all seventeen valid market values (Amsterdam through Zurich), which supplies an effective enumeration the schema lacks — no enum is defined, and the schema only gives 'e.g. Frankfurt, Milan'. That materially reduces invalid-input risk.

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 states a specific resource — the input figures of a colocation data-centre business case for one European market — and enumerates the concrete fields (construction cost per MW, colocation prices per kW-month, electricity price, staff, guarding, property tax, exit yield, grid wait, permitting, grid charges). That is far more specific than the title alone and lets an agent tell it apart from grid_connection_status or grid_carbon_and_price_now, which cover single dimensions rather than a bundled business case. It stops short of naming a sibling as the alternative, so it is clear but not explicitly differentiated.

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 context is implied rather than stated: the agent learns a personal ScienceShot key is required, that each answer consumes one run, and which markets are valid. There is no explicit when-to-use guidance nor any exclusion pointing to the sibling tools (data_centre_market_overview, grid_connection_status) for narrower questions. Adequate but with a clear routing gap.

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